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

    Neuronpedia

    INDEX
    Explanations

    statements or descriptions of positions or opinions on various subjects

    oai_token-act-pair · gpt-3.5-turbo

    mentions of personal or organizational positions on issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.90
    athan
    -0.71
    cing
    -0.68
    duct
    -0.67
    displayText
    -0.65
    amn
    -0.64
    STON
    -0.63
    actionDate
    -0.63
    amaz
    -0.63
    elta
    -0.61
    POSITIVE LOGITS
     stance
    1.33
     stances
    1.21
     toward
    0.98
     towards
    0.95
     positions
    0.89
     posture
    0.88
     position
    0.87
     reversal
    0.84
    olson
    0.76
    senal
    0.76
    Act Density 0.023%

    No Known Activations