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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation and sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.81
     yourselves
    -0.68
    themselves
    -0.67
    กัน
    -0.59
     själva
    -0.58
     us
    -0.55
     birbir
    -0.54
     esigenze
    -0.54
     kanilang
    -0.54
    Референце
    -0.54
    POSITIVE LOGITS
     myself
    1.21
     Myself
    0.96
    myself
    0.92
     myſelf
    0.90
     my
    0.79
    ArgsConstructor
    0.75
     personally
    0.69
     mijn
    0.67
    我的
    0.65
    providedIn
    0.65
    Act Density 0.216%

    No Known Activations