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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks used to indicate emotions or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.99
     Brenn
    -0.84
     ſever
    -0.83
     fevere
    -0.83
     doubtnut
    -0.82
     raiſ
    -0.82
     Efq
    -0.82
    wiſe
    -0.80
     uſed
    -0.80
     PWN
    -0.80
    POSITIVE LOGITS
     :
    1.82
     ;
    1.27
     :-
    1.17
    ::::::::
    1.09
     :\\
    1.08
     :\
    1.02
     !
    1.00
     :}
    0.98
     ：
    0.95
     :{
    0.95
    Act Density 0.296%

    No Known Activations