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

    Neuronpedia

    INDEX
    Explanations

    references to food and dining etiquette

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

    sitting, leaning, actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    walking
    -0.81
     walking
    -0.75
     walk
    -0.74
     WALK
    -0.74
    Walking
    -0.73
    walk
    -0.73
     walks
    -0.73
    WALK
    -0.71
     Walking
    -0.71
    walks
    -0.70
    POSITIVE LOGITS
     sipping
    0.48
    :✨
    0.47
     leaned
    0.46
     recl
    0.44
     backrest
    0.43
    verifyException
    0.43
     ashtray
    0.43
     sip
    0.42
     reclining
    0.41
     leaning
    0.40
    Act Density 0.052%

    No Known Activations