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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinion or belief

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.71
    Vers
    -0.68
    yna
    -0.65
    ologne
    -0.65
    soDeliveryDate
    -0.63
    autions
    -0.63
    incial
    -0.63
    emetery
    -0.61
    omics
    -0.60
    rawled
    -0.60
    POSITIVE LOGITS
     anymore
    0.90
     anybody
    0.90
     anything
    0.86
     anyone
    0.83
     nor
    0.78
     whatsoever
    0.77
     any
    0.74
    otine
    0.73
    fy
    0.73
    76561
    0.71
    Act Density 0.040%

    No Known Activations