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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptions of physical appearance

    oai_token-act-pair · gpt-3.5-turbo

    negative quality descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.77
    çīĪ
    -0.77
     privately
    -0.76
     guiActiveUn
    -0.69
     frenzy
    -0.68
     Ventura
    -0.68
     Anarchy
    -0.67
    ADRA
    -0.65
     hysteria
    -0.64
     Blanc
    -0.63
    POSITIVE LOGITS
    sounding
    1.53
    looking
    1.42
    minded
    1.38
    enough
    1.35
    eyed
    1.31
    skinned
    1.16
    footed
    1.11
    hearted
    1.09
    yet
    1.09
    earth
    1.09
    Act Density 0.078%

    No Known Activations