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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "action" in various contexts

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

    action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.54
     Kobayashi
    -0.46
     незавершена
    -0.46
    してみると
    -0.44
     TestBed
    -0.41
    Todavía
    -0.41
     Méditerranée
    -0.40
    Esperamos
    -0.39
     Seventy
    -0.39
     lemari
    -0.39
    POSITIVE LOGITS
     action
    1.93
     Action
    1.82
     ACTION
    1.74
    action
    1.72
    Action
    1.70
    ACTION
    1.45
    getAction
    1.44
     acción
    1.40
     Actions
    1.37
     actions
    1.32
    Act Density 0.024%

    No Known Activations