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

    Neuronpedia

    INDEX
    Explanations

    action verbs and decision-making processes

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

    Preceding a word before "instead"

    np_acts-logits-general · gemini-2.0-flash

    instead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.60
     Exactos
    -0.58
    yntaxException
    -0.57
    CloseOperation
    -0.56
     MediatR
    -0.54
    ArrowToggle
    -0.53
    bbene
    -0.52
     Mérimée
    -0.52
     Roskov
    -0.52
    tonsoft
    -0.52
    POSITIVE LOGITS
     instead
    4.18
     Instead
    3.84
    Instead
    3.79
    instead
    3.67
     вместо
    2.71
     istället
    2.70
     invece
    2.64
    tdessen
    2.37
     zamiast
    2.34
    代わりに
    2.23
    Act Density 0.843%

    No Known Activations