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

    Neuronpedia

    INDEX
    Explanations

    similes and comparisons using the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utsch
    -0.16
    ób
    -0.15
    zeit
    -0.14
    .synthetic
    -0.14
    etsk
    -0.14
    bew
    -0.14
    perm
    -0.14
     Feed
    -0.14
    anes
    -0.13
    Feed
    -0.13
    POSITIVE LOGITS
     clock
    0.17
    usu
    0.16
     Twe
    0.15
     charm
    0.14
    uji
    0.14
    _absolute
    0.14
    617
    0.14
    osu
    0.14
     Merk
    0.14
     McMahon
    0.14
    Act Density 0.096%

    No Known Activations