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

    Neuronpedia

    INDEX
    Explanations

    phrases related to difficult or challenging experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical or cultural entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.86
     stunt
    -0.73
    SPONSORED
    -0.72
    regor
    -0.69
    DCS
    -0.68
    Magikarp
    -0.68
     sunscreen
    -0.67
    Redd
    -0.66
    Story
    -0.65
    aeda
    -0.64
    POSITIVE LOGITS
    arte
    0.86
     alle
    0.82
    ond
    0.74
    ó
    0.74
     thou
    0.73
    ande
    0.72
     vi
    0.71
    cknowled
    0.71
     Translation
    0.70
     tion
    0.69
    Act Density 0.186%

    No Known Activations