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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating totality or inclusiveness

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

    quantifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InstanceState
    -0.36
    OGND
    -0.36
    VersionUID
    -0.35
     تضيفلها
    -0.33
     szerint
    -0.32
    ModelAdmin
    -0.32
     âges
    -0.31
     geográfica
    -0.30
    ミア
    -0.30
     is
    -0.29
    POSITIVE LOGITS
     Infórmanos
    0.83
    ftagPool
    0.73
    transQ
    0.71
     typelib
    0.69
     ſche
    0.68
     Verſ
    0.68
     виправивши
    0.68
     ſte
    0.68
    tvguidetime
    0.67
     verſ
    0.66
    Act Density 0.077%

    No Known Activations