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

    Neuronpedia

    INDEX
    Explanations

    references to different genres and styles in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens appearing after "to"

    np_acts-logits-general · gemini-2.0-flash

    classic and traditional styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.58
     milliers
    -0.56
     públicas
    -0.56
     correctes
    -0.55
    AtIndexPath
    -0.55
    gena
    -0.55
    maris
    -0.55
     dignité
    -0.54
     égale
    -0.54
     armées
    -0.54
    POSITIVE LOGITS
     classics
    0.72
     classic
    0.72
    oredCriteria
    0.69
     pure
    0.66
     beginnetje
    0.64
    それとも
    0.63
     traditional
    0.63
    theoremstyle
    0.59
    nościo
    0.58
     classical
    0.56
    Act Density 0.282%

    No Known Activations