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

    Neuronpedia

    INDEX
    Explanations

    the presence of structured document elements or metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onAnimation
    -0.65
    /
    -0.53
     &
    -0.51
     /
    -0.51
     and
    -0.50
    GenerationType
    -0.48
    MeasureSpec
    -0.46
     [
    -0.46
    TagHelper
    -0.44
    )/(
    -0.44
    POSITIVE LOGITS
    ſelves
    0.96
     itſelf
    0.86
    ſelf
    0.84
     myſelf
    0.83
     Majefty
    0.81
     Monfieur
    0.79
     Houſe
    0.78
     Efq
    0.77
     doubtnut
    0.77
     Anſ
    0.75
    Act Density 0.401%

    No Known Activations