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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opinions or positions on certain issues

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opinions or positions on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.85
    duct
    -0.69
    cing
    -0.68
     Tycoon
    -0.68
    STON
    -0.67
    athan
    -0.65
    esters
    -0.64
    rafted
    -0.63
    amn
    -0.63
    IVERS
    -0.63
    POSITIVE LOGITS
     stance
    1.30
     stances
    1.16
     toward
    0.92
     posture
    0.86
     towards
    0.86
     positions
    0.85
     position
    0.85
     reversal
    0.78
     views
    0.75
     pledge
    0.74
    Act Density 0.024%

    No Known Activations