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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of being or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jíma
    -0.57
    ########.
    -0.55
    رشف
    -0.54
     /\.(
    -0.53
    もった
    -0.52
    atshirt
    -0.52
     locura
    -0.50
     kuhusu
    -0.48
    OGND
    -0.48
     Atlántico
    -0.48
    POSITIVE LOGITS
     להיות
    0.82
     soyez
    0.74
    Be
    0.73
     être
    0.69
     be
    0.68
     Be
    0.68
    (!__
    0.67
    Будь
    0.67
     being
    0.67
    Being
    0.64
    Act Density 0.319%

    No Known Activations