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

    Neuronpedia

    INDEX
    Explanations

    words related to permission or enabling actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iche
    -0.15
    yt
    -0.15
    ventus
    -0.14
    ril
    -0.14
    alent
    -0.14
    svp
    -0.14
    ething
    -0.14
    aeda
    -0.14
    ichel
    -0.14
    hsi
    -0.14
    POSITIVE LOGITS
     us
    0.27
    ance
    0.24
    fullscreen
    0.23
    ances
    0.21
     him
    0.20
     for
    0.18
     flexibility
    0.18
     them
    0.18
    /dis
    0.18
    /disable
    0.18
    Act Density 0.051%

    No Known Activations