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

    Neuronpedia

    INDEX
    Explanations

    notations or references related to numerical values and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     legales
    -0.58
    AppCompat
    -0.56
    GenerationType
    -0.54
    CJK
    -0.52
    PreAuthorize
    -0.50
     remercier
    -0.49
    bufio
    -0.49
    Immutable
    -0.46
    indale
    -0.46
    bunch
    -0.46
    POSITIVE LOGITS
    expandindo
    0.80
    ktop
    0.59
     Zer
    0.58
    Portale
    0.55
    חור
    0.54
    发表于
    0.53
    UpInside
    0.53
     InputDecoration
    0.52
    tagHelperRunner
    0.51
    AutoScaleMode
    0.50
    Act Density 0.475%

    No Known Activations