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

    Neuronpedia

    INDEX
    Explanations

    instances or phrases that emphasize specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    slidesToShow
    -0.91
    setDo
    -0.80
     ​​
    -0.79
     useEffect
    -0.79
    awtextra
    -0.78
     ItemStack
    -0.77
     Doris
    -0.77
    idavit
    -0.77
    ButtonModule
    -0.76
    estors
    -0.76
    POSITIVE LOGITS
     particular
    0.92
    ticularly
    0.91
     particulares
    0.90
    particular
    0.84
     Particular
    0.83
    Particular
    0.83
     PARTICULAR
    0.82
     partic
    0.82
    ity
    0.81
     Particulars
    0.64
    Act Density 0.099%

    No Known Activations