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

    Neuronpedia

    INDEX
    Explanations

    occurrences of structured elements or data definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.60
     (
    -0.55
    man
    -0.55
    ala
    -0.54
    al
    -0.54
    InitVars
    -0.53
     unknownFields
    -0.52
    posedge
    -0.52
    bParam
    -0.52
    men
    -0.52
    POSITIVE LOGITS
    存于互联网档案馆
    0.96
     houſe
    0.94
     Houſe
    0.93
    expandindo
    0.92
    Hochspringen
    0.84
     purpoſe
    0.82
     Diſ
    0.80
    ſelves
    0.80
     المعيارى
    0.74
     pleaſure
    0.73
    Act Density 0.216%

    No Known Activations