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

    Neuronpedia

    INDEX
    Explanations

    references to visual media or posters in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sel
    -0.35
    sWith
    -0.35
    sm
    -0.34
    sp
    -0.33
    side
    -0.33
    son
    -0.33
    sh
    -0.33
    sw
    -0.32
    sc
    -0.32
    sin
    -0.32
    POSITIVE LOGITS
    idge
    0.32
    er
    0.30
    cury
    0.29
    ë§ģ
    0.29
    gebn
    0.29
    lain
    0.28
    ed
    0.27
    ific
    0.27
    most
    0.26
    azzi
    0.25
    Act Density 0.708%

    No Known Activations