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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and significant terms associated with popular culture and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wallace
    -0.17
    rama
    -0.16
    ARGIN
    -0.16
    erge
    -0.14
    _tokenize
    -0.14
    Cargo
    -0.14
    ama
    -0.14
    åĭ¢
    -0.14
    arna
    -0.14
    ãĥ¼ãĥĢ
    -0.14
    POSITIVE LOGITS
    illions
    0.15
    undred
    0.15
    ifr
    0.15
    Leod
    0.15
    assi
    0.15
     incident
    0.14
    iyon
    0.14
    ála
    0.14
    leigh
    0.14
    /maps
    0.14
    Act Density 0.394%

    No Known Activations