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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activity and social issues

    oai_token-act-pair · gpt-3.5-turbo

    titles or topics related to personal experiences and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     toget
    -0.63
    etsk
    -0.60
    auth
    -0.58
     acknow
    -0.57
    dyl
    -0.56
    rising
    -0.56
    âĶĢâĶĢâĶĢâĶĢ
    -0.54
    iannopoulos
    -0.54
    cellaneous
    -0.53
     storm
    -0.53
    POSITIVE LOGITS
     Guys
    0.76
     Club
    0.72
    ifacts
    0.70
     Cycle
    0.70
     Complex
    0.69
     Them
    0.68
     Products
    0.68
     Purpose
    0.68
     Than
    0.68
     Parties
    0.67
    Act Density 0.760%

    No Known Activations