Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to specific subjects or topics, as it seems to be scanning for specific terms such as "Star Trek," "natural gas," "CrossFit," "climate change," "resident evil 5," "social security," "forest degradation," among others

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases associated with popular culture, socio-political issues, and fitness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.77
    SY
    -0.76
    Large
    -0.67
    ãĥ¥
    -0.66
    minecraft
    -0.66
    thumbnails
    -0.66
    NW
    -0.66
    Merit
    -0.66
    Columb
    -0.65
    rez
    -0.64
    POSITIVE LOGITS
     rul
    0.71
     issu
    0.68
    eers
    0.67
     basics
    0.65
     fundamentals
    0.65
     equivalents
    0.60
     Basics
    0.59
     guid
    0.59
     targ
    0.58
    amily
    0.58
    Act Density 0.482%

    No Known Activations