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

    Neuronpedia

    INDEX
    Explanations

    actions or activities that involve physical engagement

    oai_token-act-pair · gpt-3.5-turbo

    actions and activities related to social interactions and personal habits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taboola
    -0.72
    Enlarge
    -0.67
    heter
    -0.66
    pmwiki
    -0.64
    Jer
    -0.63
    tesy
    -0.62
    terness
    -0.61
    ple
    -0.59
    igl
    -0.57
    thur
    -0.56
    POSITIVE LOGITS
    '."
    0.65
     oneself
    0.63
    alogue
    0.61
    èĢħ
    0.61
    ',"
    0.60
     corrid
    0.60
     equivalents
    0.60
    ij士
    0.59
     rul
    0.58
    Tokens
    0.58
    Act Density 0.977%

    No Known Activations