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

    Neuronpedia

    INDEX
    Explanations

    adjectives or nouns related to perceptions or feelings

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to emotions and subjective perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbn
    -0.79
    perty
    -0.70
    cue
    -0.66
    sight
    -0.65
    nect
    -0.65
    hooting
    -0.64
    videos
    -0.64
    ices
    -0.64
    aband
    -0.63
    eni
    -0.63
    POSITIVE LOGITS
     urgency
    0.71
     unanim
    0.70
     acknowledgement
    0.66
    IENT
    0.66
     linkage
    0.66
     that
    0.65
     belief
    0.64
     impat
    0.64
     reluctance
    0.64
     pervasive
    0.63
    Act Density 0.187%

    No Known Activations