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

    Neuronpedia

    INDEX
    Explanations

    programming concepts related to class and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oler
    -0.19
     log
    -0.16
     rect
    -0.16
     grey
    -0.16
     sign
    -0.16
     t
    -0.15
     se
    -0.15
     fr
    -0.15
     dis
    -0.15
     obs
    -0.15
    POSITIVE LOGITS
     putas
    0.16
     бли
    0.15
    -Allow
    0.15
    اÙĤ
    0.14
     CreateMap
    0.14
     porr
    0.14
    aklı
    0.14
    UTH
    0.14
    .sz
    0.14
    ampo
    0.14
    Act Density 0.123%

    No Known Activations