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

    Neuronpedia

    INDEX
    Explanations

    references to staff or personnel in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olian
    -0.16
    orget
    -0.15
    cho
    -0.15
    abaj
    -0.15
    uki
    -0.15
    ymm
    -0.15
    ÑĩеÑĢ
    -0.14
    ارÙĬØ®
    -0.14
    ext
    -0.14
    abolic
    -0.14
    POSITIVE LOGITS
    s
    0.19
    ord
    0.19
    neck
    0.18
    sville
    0.18
    ulty
    0.18
    ed
    0.18
    ioni
    0.17
    room
    0.17
    ORD
    0.17
    _codegen
    0.17
    Act Density 0.020%

    No Known Activations