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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ^(@)
    -0.79
     SafeMath
    -0.76
    ](#
    -0.75
    uxxxx
    -0.73
    MLLoader
    -0.73
    PreferredItem
    -0.72
    NameInMap
    -0.72
    öße
    -0.70
     CURLOPT
    -0.70
    Eqn
    -0.70
    POSITIVE LOGITS
    na
    0.48
    gól
    0.47
    —
    0.46
    im
    0.45
    (
    0.45
    ((
    0.43
    .
    0.43
    St
    0.43
    Sweet
    0.43
    I
    0.42
    Act Density 0.031%

    No Known Activations