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

    Neuronpedia

    INDEX
    Explanations

    phrases related to beliefs, opinions, conclusions, and changes in perspective

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating realization or change in perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gonna
    -0.80
     To
    -0.70
    quickShipAvailable
    -0.69
     teasp
    -0.63
     gotta
    -0.63
     Going
    -0.63
     meantime
    -0.63
     Uz
    -0.60
    To
    -0.59
     Tra
    -0.58
    POSITIVE LOGITS
    uate
    1.03
    enance
    1.02
    peak
    0.80
    ilial
    0.75
    dress
    0.74
    ulate
    0.74
    igate
    0.70
    ional
    0.70
    ties
    0.66
    ISE
    0.64
    Act Density 0.469%

    No Known Activations