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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate purpose or outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BrowserModule
    -0.59
    :+:
    -0.58
    UrlResolution
    -0.56
     Italijanski
    -0.50
    ########.
    -0.48
    KommentareTeilen
    -0.45
    migo
    -0.44
    脚注の使い方
    -0.44
    AsUp
    -0.43
    BeginContext
    -0.43
    POSITIVE LOGITS
    othed
    0.75
     hopefully
    0.73
     înc
    0.63
     they
    0.61
    called
    0.60
     presumably
    0.57
     pastikan
    0.55
     far
    0.55
     please
    0.52
     adelante
    0.52
    Act Density 0.130%

    No Known Activations