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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.92
     Reſ
    -1.69
     Diſ
    -1.67
     myſelf
    -1.66
     Majefty
    -1.64
     Anſ
    -1.63
     ſeveral
    -1.61
     photolibrary
    -1.57
     doubtnut
    -1.56
     greateſt
    -1.56
    POSITIVE LOGITS
     I
    1.22
     y
    1.16
     A
    1.14
     et
    1.13
     
    1.12
     m
    1.12
     i
    1.11
     s
    1.10
     v
    1.08
     l
    1.08
    Act Density 2.220%

    No Known Activations