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

    Neuronpedia

    INDEX
    Explanations

    superlative forms and references to significant achievements or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.68
    CloseOperation
    -0.58
    Personendaten
    -0.56
    ContentLoaded
    -0.48
    IsMutable
    -0.47
     Enough
    -0.47
     insuffisamment
    -0.45
    ">—
    -0.44
    脚注の使い方
    -0.44
    WireFormatLite
    -0.44
    POSITIVE LOGITS
     ever
    1.52
     imaginable
    1.37
     EVER
    1.21
    ever
    1.11
     ooit
    1.04
     possible
    0.99
     jemals
    0.98
     überhaupt
    0.96
     conceivable
    0.95
    EVER
    0.94
    Act Density 0.304%

    No Known Activations