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

    Neuronpedia

    INDEX
    Explanations

    feedback and references to actions regarding decision-making and implementations

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

    Preceding tokens of "action"

    np_acts-logits-general · gemini-2.0-flash

    love in action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.60
    brtc
    -0.54
     contextLoads
    -0.50
     ModelExpression
    -0.49
    Interview
    -0.48
     맞
    -0.47
     Interviews
    -0.47
     Esti
    -0.46
     INTERVIEW
    -0.44
    hten
    -0.44
    POSITIVE LOGITS
     action
    4.17
    action
    3.62
     Action
    3.47
    Action
    3.37
     ACTION
    3.21
    ACTION
    2.90
     actions
    2.90
     acción
    2.88
     ação
    2.60
     Actions
    2.59
    Act Density 0.298%

    No Known Activations