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

    Neuronpedia

    INDEX
    Explanations

    specific technical notations or variables in mathematical or scientific expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    randomUUID
    -0.66
     sv
    -0.58
    NewGuid
    -0.55
    penup
    -0.55
    orteur
    -0.53
    Sv
    -0.52
     idéia
    -0.52
    JdbcTemplate
    -0.52
     svo
    -0.51
    newArrayList
    -0.50
    POSITIVE LOGITS
    Personensuche
    0.81
    DispatchToProps
    0.68
    <bos>
    0.64
     transférez
    0.63
    Hochspringen
    0.63
     HasFactory
    0.62
    pensive
    0.59
    χρι
    0.56
    mallow
    0.56
    الدراسه
    0.56
    Act Density 0.220%

    No Known Activations