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

    Neuronpedia

    INDEX
    Explanations

    code-related keywords and annotations, particularly those associated with class and entity definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç¯
    -0.14
    indr
    -0.14
    borough
    -0.14
    egra
    -0.14
    atur
    -0.14
     const
    -0.14
    needle
    -0.13
    cker
    -0.13
     Entr
    -0.13
    aul
    -0.13
    POSITIVE LOGITS
     Base
    0.38
     base
    0.37
    Base
    0.34
    base
    0.31
    _base
    0.30
    .Base
    0.29
    .base
    0.28
    -base
    0.28
    åŁº
    0.28
     BaseModel
    0.27
    Act Density 0.105%

    No Known Activations