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

    Neuronpedia

    INDEX
    Explanations

    social media-related call-to-action terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the end-of-document token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minist
    -0.81
    pite
    -0.75
     ILCS
    -0.72
    endiary
    -0.70
    illac
    -0.66
    anyon
    -0.62
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.62
    inese
    -0.61
    bably
    -0.61
     coerced
    -0.61
    POSITIVE LOGITS
     @
    0.94
    ers
    0.87
     Stories
    0.86
    ed
    0.84
    ership
    0.84
    Sym
    0.84
     HuffPost
    0.78
     Trend
    0.75
     Follow
    0.72
     Updates
    0.71
    Act Density 0.022%

    No Known Activations