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

    Neuronpedia

    INDEX
    Explanations

    mentions of feelings or perceptions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "sense" or subjective perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.82
    sites
    -0.82
    onial
    -0.78
    morrow
    -0.71
    dule
    -0.65
    zac
    -0.65
    solete
    -0.64
    emort
    -0.64
    mercial
    -0.63
    ceed
    -0.63
    POSITIVE LOGITS
    ively
    0.90
     urgency
    0.79
    omatic
    0.78
    IFT
    0.77
     sense
    0.75
    ibility
    0.75
    UAL
    0.75
     deprivation
    0.73
     compulsion
    0.72
    ibly
    0.71
    Act Density 0.026%

    No Known Activations