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

    Neuronpedia

    INDEX
    Explanations

    references to specific variable names and class definitions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    日閲覧
    -0.81
    *************
    -0.78
    __':
    -0.74
    __":
    -0.74
    ]**
    -0.73
    .}~\
    -0.72
     ་་
    -0.70
     NavController
    -0.69
     Pozna
    -0.68
    脚注の使い方
    -0.68
    POSITIVE LOGITS
    h
    2.16
     h
    2.02
    ｈ
    1.12
    H
    1.09
    hh
    1.03
    rh
    1.02
    fh
    1.00
    setH
    1.00
    eh
    0.99
    ℎ
    0.93
    Act Density 0.097%

    No Known Activations