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

    Neuronpedia

    INDEX
    Explanations

    reference to notable historical figures and terms related to cultural and social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.28
    sh
    -0.26
    sc
    -0.26
    sm
    -0.24
    sWith
    -0.24
    sp
    -0.24
    sid
    -0.24
    set
    -0.23
    sel
    -0.23
    sr
    -0.23
    POSITIVE LOGITS
    er
    0.27
    cury
    0.26
    ød
    0.25
    ë§ģ
    0.24
    idge
    0.24
    lain
    0.24
    hyth
    0.23
    theless
    0.23
    erer
    0.22
    most
    0.22
    Act Density 0.887%

    No Known Activations