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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to previews and early announcements in various contexts

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

    coming before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prüche
    -0.50
    hiasan
    -0.47
    temuan
    -0.45
     scolaire
    -0.43
    Referències
    -0.42
     senhora
    -0.42
     yks
    -0.42
     spécialisée
    -0.42
    Kariera
    -0.41
     chrétienne
    -0.40
    POSITIVE LOGITS
     preview
    0.84
     anticipation
    0.82
     Preview
    0.75
     foreshadow
    0.72
     preparatory
    0.71
     anticip
    0.71
     preliminary
    0.70
    PreExecute
    0.67
     precursor
    0.66
     foret
    0.66
    Act Density 0.048%

    No Known Activations