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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs indicating readiness or preparation for actions

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

    ready to act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stays
    -0.46
    要知道
    -0.44
    LLOW
    -0.42
    stays
    -0.42
     Stays
    -0.41
    Xna
    -0.40
    すること
    -0.40
    🔕
    -0.39
     bodem
    -0.39
    setHorizontal
    -0.38
    POSITIVE LOGITS
     ready
    0.71
     Ready
    0.70
    Ready
    0.62
     READY
    0.61
     listos
    0.59
    ready
    0.55
    READY
    0.53
     pronti
    0.49
    tagHelperRunner
    0.47
     prêts
    0.47
    Act Density 0.020%

    No Known Activations