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

    Neuronpedia

    INDEX
    Explanations

    references to shadows and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzleHttp
    -0.39
    bringung
    -0.38
     critères
    -0.38
    maakt
    -0.37
     bör
    -0.37
     comprends
    -0.36
     fédé
    -0.36
    ywna
    -0.36
     journées
    -0.35
    ifiquement
    -0.35
    POSITIVE LOGITS
     shadow
    1.43
    shadow
    1.30
     SHADOW
    1.27
     Shadow
    1.27
     shadows
    1.24
    Shadow
    1.22
    SHADOW
    1.13
     Shadows
    1.12
    hadow
    1.08
    Shadows
    1.07
    Act Density 0.254%

    No Known Activations