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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific items or entities being marked or ranked

    oai_token-act-pair · gpt-3.5-turbo

    attributes related to rankings and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anew
    -0.61
    ummer
    -0.59
    Newsletter
    -0.53
     Weeks
    -0.52
     stabilize
    -0.47
    -,
    -0.44
     hemor
    -0.44
     --
    -0.44
     antic
    -0.43
    ,...
    -0.42
    POSITIVE LOGITS
    atsuki
    0.59
     lyrics
    0.58
     vocals
    0.56
     homophobic
    0.55
     Cosponsors
    0.55
     clitor
    0.54
    texture
    0.53
     pupils
    0.53
    ãĥ¡
    0.51
     UKIP
    0.51
    Act Density 1.803%

    No Known Activations