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

    Neuronpedia

    INDEX
    Explanations

    action verbs indicating performance or behavior

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference actions or behaviors being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usk
    -0.72
    isphere
    -0.65
    addon
    -0.64
    selection
    -0.61
    inen
    -0.61
    atto
    -0.60
    iHUD
    -0.60
    irl
    -0.59
    osa
    -0.58
    apsed
    -0.58
    POSITIVE LOGITS
     deserve
    1.13
     offend
    1.07
     mattered
    1.02
     aren
    1.00
     resonate
    0.95
     weren
    0.93
     nobody
    0.93
     enrich
    0.92
    rouse
    0.91
     shouldn
    0.90
    Act Density 0.188%

    No Known Activations