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

    Neuronpedia

    INDEX
    Explanations

    financial or business-related terms

    oai_token-act-pair · gpt-3.5-turbo

    nouns and concepts related to significant societal and personal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebin
    -0.77
    +.
    -0.75
     attRot
    -0.69
    %.
    -0.66
    .).
    -0.65
    .''.
    -0.61
    ãĢĤ
    -0.58
     versa
    -0.58
    ().
    -0.58
    '.
    -0.58
    POSITIVE LOGITS
     of
    0.84
     aboard
    0.59
    weet
    0.59
     surrounding
    0.56
     plag
    0.56
     throughout
    0.55
     in
    0.55
     belonging
    0.55
    outhern
    0.54
     inside
    0.53
    Act Density 0.795%

    No Known Activations