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

    Neuronpedia

    INDEX
    Explanations

    statements related to legal or criminal activities, specifically focusing on individuals or actions

    oai_token-act-pair · gpt-3.5-turbo

    important individuals or roles in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conver
    -0.69
     converge
    -0.64
     equivalent
    -0.64
     respectively
    -0.63
    ideon
    -0.63
     common
    -0.63
    iosyncr
    -0.62
     societies
    -0.61
    orns
    -0.60
     collective
    -0.60
    POSITIVE LOGITS
    âĹ¼
    0.76
    henko
    0.74
    tesy
    0.71
     Targ
    0.68
    bilt
    0.67
     personally
    0.67
    Film
    0.66
     himself
    0.65
    enegger
    0.64
    Care
    0.63
    Act Density 0.443%

    No Known Activations