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

    Neuronpedia

    INDEX
    Explanations

    technical terms and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nya
    -0.77
    ました
    -0.74
    ます
    -0.70
    səhifə
    -0.65
    ۰
    -0.63
    نا
    -0.60
    ない
    -0.57
    ness
    -0.57
    ly
    -0.56
    balleur
    -0.55
    POSITIVE LOGITS
    깐
    0.56
    y
    0.46
    yi
    0.44
    ی
    0.41
    yu
    0.40
    til
    0.39
    yoga
    0.38
    yet
    0.38
    yee
    0.38
    yog
    0.37
    Act Density 0.516%

    No Known Activations