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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-3.5-turbo

    initials or abbreviations related to names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thereof
    -0.74
    EStream
    -0.72
     ().
    -0.71
     ______
    -0.71
    åĤ
    -0.71
     blah
    -0.70
     ;)
    -0.69
     Leviathan
    -0.67
     ðŁĻĤ
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    POSITIVE LOGITS
    resa
    1.23
    ogether
    1.07
    roximately
    1.01
    alyst
    1.00
    zens
    0.95
    withstanding
    0.87
    respond
    0.86
    xiety
    0.85
     spokeswoman
    0.84
    rary
    0.82
    Act Density 0.330%

    No Known Activations