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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with programming constructs and their states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.63
    ValueStyle
    -0.59
    UnsafeEnabled
    -0.56
    6
    -0.56
     OFDb
    -0.55
     sixth
    -0.53
    الدراسه
    -0.52
    Билгалдахарш
    -0.51
    .*")]
    -0.51
     contextLoads
    -0.50
    POSITIVE LOGITS
    0.80
    0.71
    Personendaten
    0.54
    __.__
    0.53
    rachtet
    0.48
     transfieras
    0.47
    empty
    0.46
    _^
    0.46
    schaft
    0.46
    ΕΙ
    0.45
    Act Density 0.034%

    No Known Activations