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

    Neuronpedia

    INDEX
    Explanations

    specific structured phrases and terminology related to evaluation and analysis in various contexts

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

    Codes, abbreviations, and acronyms

    np_acts-logits-general · gemini-2.0-flash

    Magee, Pace, Bale, Caine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.58
    IntoConstraints
    -0.56
     poitrine
    -0.54
     fourrure
    -0.54
     réputation
    -0.53
     licorne
    -0.53
     casquette
    -0.53
     autocollant
    -0.52
     personnalité
    -0.52
     laiton
    -0.52
    POSITIVE LOGITS
     Magee
    0.82
     Pace
    0.74
     Bale
    0.74
     PACE
    0.74
    ine
    0.74
    ice
    0.73
    ale
    0.72
     Caine
    0.72
     Cline
    0.72
     Dane
    0.71
    Act Density 0.418%

    No Known Activations