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

    Neuronpedia

    INDEX
    Explanations

    syntax elements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.63
    LookAnd
    -0.59
    AndEndTag
    -0.57
    ˌ
    -0.56
    SharedDtor
    -0.55
     actionMode
    -0.54
     OnInit
    -0.54
    rosion
    -0.53
    shrimp
    -0.53
     }{@
    -0.52
    POSITIVE LOGITS
     ſtate
    0.60
     itſelf
    0.56
     RMA
    0.56
     SRI
    0.55
     Cæsar
    0.55
     DLP
    0.54
     CGA
    0.53
     Sarm
    0.53
     BPI
    0.53
     SFR
    0.53
    Act Density 0.153%

    No Known Activations