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

    Neuronpedia

    INDEX
    Explanations

    elements related to flexibility and customization in choices and preferences

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

    user preferences or desired actions

    np_acts-logits-general · gemini-2.0-flash

    set or desired options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.57
    onAttach
    -0.54
    parsedMessage
    -0.51
    enderror
    -0.50
    хьтан
    -0.49
     виправивши
    -0.48
    новништво
    -0.46
    rophes
    -0.46
    featureID
    -0.44
    HideFlags
    -0.44
    POSITIVE LOGITS
     gewüns
    0.47
     gewünschten
    0.47
     dowol
    0.47
     either
    0.46
    enumi
    0.42
     choose
    0.42
     aéreo
    0.42
     desired
    0.41
    Option
    0.40
     depending
    0.40
    Act Density 0.388%

    No Known Activations