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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and separators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Vidite
    -0.98
    CrossRef
    -0.93
    Хьажоргаш
    -0.90
    kháu
    -0.88
    Filmografia
    -0.85
    kloped
    -0.84
    RegressionTest
    -0.83
     ApiException
    -0.83
    offsetof
    -0.82
    Cyfeiriadau
    -0.80
    POSITIVE LOGITS
    <
    0.74
    dillas
    0.65
    /******/
    0.57
    WEBPACK
    0.55
    というわけで
    0.55
     wenigen
    0.54
     <
    0.52
     early
    0.52
     been
    0.52
    PENT
    0.51
    Act Density 0.030%

    No Known Activations