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

    Neuronpedia

    INDEX
    Explanations

    references to specific films and associated characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Variety
    -0.15
    ogui
    -0.15
    enthal
    -0.14
    arness
    -0.14
    NIL
    -0.14
    ottom
    -0.14
    :host
    -0.14
    amax
    -0.14
    azer
    -0.14
    utenberg
    -0.14
    POSITIVE LOGITS
    FLAG
    0.18
    inox
    0.18
    Å¡em
    0.16
    ifact
    0.15
     Alliance
    0.15
     ëģ
    0.14
     exh
    0.14
    phinx
    0.14
     京
    0.14
    ibar
    0.14
    Act Density 0.009%

    No Known Activations