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

    Neuronpedia

    INDEX
    Explanations

    the word "this" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    specialchars
    -0.31
    addEventListener
    -0.27
    ArgsConstructor
    -0.27
    iguar
    -0.27
    uyez
    -0.27
    yych
    -0.25
     älskar
    -0.25
    эффици
    -0.25
    EncBinary
    -0.24
    إنه
    -0.24
    POSITIVE LOGITS
     noDo
    0.70
     acestei
    0.65
     acestui
    0.63
    ſelf
    0.57
    elemField
    0.57
     these
    0.57
     hereof
    0.57
    yntaxException
    0.57
     this
    0.57
     them
    0.56
    Act Density 0.287%

    No Known Activations