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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and informed choices

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

    making decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stag
    -0.40
     mention
    -0.38
     presentation
    -0.38
     mutagen
    -0.37
    mention
    -0.36
     nitrous
    -0.36
     sponsor
    -0.35
     Severn
    -0.35
     구
    -0.34
    Spect
    -0.34
    POSITIVE LOGITS
     Entscheidungen
    0.65
    vician
    0.59
     beginnetje
    0.59
     Entscheidung
    0.57
     decisión
    0.57
     informée
    0.55
    writeField
    0.55
    addCriterion
    0.55
     beslut
    0.54
     décision
    0.53
    Act Density 0.016%

    No Known Activations