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

    Neuronpedia

    INDEX
    Explanations

    numbers and identifiers, possibly related to versions or data entries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RTLD
    -0.57
     means
    -0.57
    SourceChecksum
    -0.57
     such
    -0.55
     which
    -0.55
     for
    -0.54
    @[+][
    -0.53
     of
    -0.52
    شهاد
    -0.52
     all
    -0.52
    POSITIVE LOGITS
     myſelf
    0.78
     ſy
    0.74
     pleaſure
    0.72
     ſeveral
    0.72
     faſt
    0.70
     ſever
    0.69
     itſelf
    0.67
     Egli
    0.67
     iſt
    0.66
    principalColumn
    0.66
    Act Density 0.126%

    No Known Activations