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

    Neuronpedia

    INDEX
    Explanations

    themes of powerlessness and choice in literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     books
    -0.17
     Books
    -0.17
     fran
    -0.16
    rama
    -0.16
     book
    -0.16
    -books
    -0.16
    rios
    -0.15
    apid
    -0.14
     helf
    -0.14
    zew
    -0.14
    POSITIVE LOGITS
     short
    0.26
    çŁŃ
    0.22
     essay
    0.22
    -short
    0.22
    short
    0.21
     shorts
    0.21
     essays
    0.21
    (short
    0.20
     Short
    0.20
    oug
    0.20
    Act Density 0.152%

    No Known Activations