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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal disputes and situations that may require legal action

    oai_token-act-pair · gpt-3.5-turbo

    references to legal proceedings and protests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anse
    -0.70
    iqueness
    -0.68
    ixture
    -0.66
     guid
    -0.57
    ulty
    -0.56
     Pos
    -0.56
     Surface
    -0.55
    GY
    -0.55
    aldi
    -0.55
    eq
    -0.54
    POSITIVE LOGITS
     voluntarily
    0.99
     willingly
    0.86
     expecting
    0.83
     ASAP
    0.80
     again
    0.78
     hoping
    0.74
     bandwagon
    0.74
     prematurely
    0.73
     unprepared
    0.72
     invol
    0.72
    Act Density 0.261%

    No Known Activations