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

    Neuronpedia

    INDEX
    Explanations

    causal relationships or reasons behind statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ấp
    -0.15
    onna
    -0.15
    iffe
    -0.15
    ele
    -0.14
    ertz
    -0.14
    nda
    -0.14
    neh
    -0.14
    /schema
    -0.14
    ernels
    -0.13
    REQ
    -0.13
    POSITIVE LOGITS
    ÑĦоÑĢ
    0.18
     Merrill
    0.16
    stå
    0.16
    à¥Īत
    0.16
    SizePolicy
    0.15
    ç«ĭãģ¦
    0.14
    _ASSUME
    0.14
    ALLERY
    0.14
     Cab
    0.14
    лаж
    0.14
    Act Density 0.082%

    No Known Activations