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

    Neuronpedia

    INDEX
    Explanations

    words indicating relationships or interactions between services and users

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adequate
    -0.15
    adÄĽ
    -0.14
    ansi
    -0.14
    /trunk
    -0.14
    aders
    -0.14
    -opacity
    -0.13
    :black
    -0.13
     nedost
    -0.13
    fullscreen
    -0.13
    .fixed
    -0.13
    POSITIVE LOGITS
     small
    0.29
     smaller
    0.28
     smallest
    0.26
    small
    0.26
     tiny
    0.25
    -small
    0.25
     SMALL
    0.25
    å°ı
    0.24
     peque
    0.23
     Small
    0.22
    Act Density 0.017%

    No Known Activations