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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating excitement and accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "we" and its variants, indicating collective sentiment or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itates
    -0.65
    Appearances
    -0.64
     Flavoring
    -0.62
    itary
    -0.57
     offending
    -0.57
    rift
    -0.57
    uces
    -0.56
    Pref
    -0.56
    entary
    -0.55
    dust
    -0.55
    POSITIVE LOGITS
    're
    1.34
    've
    1.27
     intend
    1.08
     anticipate
    1.07
     are
    1.00
     strive
    0.98
    akening
    0.92
     believe
    0.92
     hope
    0.90
    'll
    0.90
    Act Density 0.198%

    No Known Activations