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

    Neuronpedia

    INDEX
    Explanations

    numerical values or statistics related to scientific findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -2.48
     itſelf
    -2.44
     Efq
    -2.15
     pleaſure
    -2.14
     purpoſe
    -2.10
     houſe
    -2.07
     Jefus
    -2.06
     Monfieur
    -2.01
     himſelf
    -2.00
    ſelf
    -2.00
    POSITIVE LOGITS
    <eos>
    2.30
    ↵↵
    1.51
     
    1.20
    ,
    1.14
     (
    1.08
    '
    1.03
     -
    1.00
    -
    0.99
    :
    0.97
     "
    0.93
    Act Density 0.304%

    No Known Activations