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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific terms in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to attribution and conditions related to events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <?
    -0.82
    odore
    -0.68
    aeda
    -0.67
     ILCS
    -0.65
    Õ
    -0.65
     Blueprint
    -0.65
     Cosponsors
    -0.64
     Rivals
    -0.61
    AKING
    -0.61
     Colors
    -0.60
    POSITIVE LOGITS
     occurs
    0.88
     happens
    0.86
     progresses
    0.85
     desired
    0.80
     arises
    0.79
     progressed
    0.78
     transitioned
    0.78
     transpired
    0.77
     warranted
    0.76
     existed
    0.75
    Act Density 0.340%

    No Known Activations