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

    Neuronpedia

    INDEX
    Explanations

    expressions of sentiment and personal qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emales
    -0.17
     fury
    -0.16
     Fury
    -0.15
     guts
    -0.15
    alance
    -0.14
    agua
    -0.14
    rita
    -0.14
     jel
    -0.14
    ãģ¾ãĤĮ
    -0.14
     celebrated
    -0.14
    POSITIVE LOGITS
     thrilling
    0.17
     thrilled
    0.17
     Pathfinder
    0.17
     thrill
    0.16
    indr
    0.16
     hourly
    0.15
    mute
    0.15
    rans
    0.15
     entrev
    0.15
     gay
    0.14
    Act Density 0.138%

    No Known Activations