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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and readings around conditional and situational phrases

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    )"),
    -0.54
    '}),
    -0.52
    __);
    -0.49
     =~
    -0.48
    sund
    -0.47
    haustible
    -0.47
    ocally
    -0.46
    urel
    -0.44
    liseum
    -0.44
    ':{
    -0.44
    POSITIVE LOGITS
     Wikimedijinoj
    0.73
     InputDecoration
    0.71
    НИК
    0.67
    例句
    0.66
    CLUYE
    0.66
    Occurs
    0.65
     happens
    0.65
     تضيفلها
    0.65
    happens
    0.64
    ENED
    0.64
    Act Density 0.018%

    No Known Activations