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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "actions."

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

    actions followed by verbs or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rigue
    -0.53
     createSlice
    -0.53
     quadrature
    -0.52
     iconFacebook
    -0.50
    InputBorder
    -0.50
    InputTagHelper
    -0.50
    parsedMessage
    -0.49
     незавершена
    -0.49
    かというと
    -0.49
     galore
    -0.49
    POSITIVE LOGITS
     actions
    1.70
     Actions
    1.53
    Actions
    1.38
    actions
    1.36
     ACTIONS
    1.27
     acciones
    1.12
     azioni
    1.01
     ações
    0.96
    ACTIONS
    0.91
     Handlungen
    0.90
    Act Density 0.013%

    No Known Activations