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

    Neuronpedia

    INDEX
    Explanations

    titles and phrases related to movie reviews and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gould
    -0.15
    TED
    -0.15
     Setter
    -0.14
     TED
    -0.14
     Fol
    -0.14
     Temper
    -0.14
     extract
    -0.14
     Getty
    -0.14
     Polo
    -0.14
    ABC
    -0.13
    POSITIVE LOGITS
     reviews
    0.18
    reviews
    0.18
     Reviews
    0.18
    Reviews
    0.18
     breakdown
    0.16
     æ¼
    0.16
     retro
    0.16
     podcast
    0.15
     SEXP
    0.15
    виÑĩ
    0.15
    Act Density 0.125%

    No Known Activations