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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotations or quoted speech within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reckoning
    -0.75
     feas
    -0.74
     probable
    -0.74
     flock
    -0.72
     brim
    -0.71
     honor
    -0.71
     possibility
    -0.70
     rhy
    -0.69
     halfway
    -0.68
     toast
    -0.68
    POSITIVE LOGITS
    âĢ¦]
    2.03
    ...]
    1.96
    english
    1.30
    REDACTED
    1.25
    Laughs
    1.22
    Pg
    1.22
    ?]
    1.19
    !]
    1.17
    T
    1.11
    ']
    1.11
    Act Density 0.025%

    No Known Activations