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

    Neuronpedia

    INDEX
    Explanations

    references to scientific classifications or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inalg
    -0.16
    _lhs
    -0.15
    âk
    -0.14
    éĻµ
    -0.14
    dff
    -0.14
    lobby
    -0.14
    ¯u
    -0.14
     वस
    -0.14
     лиÑĨа
    -0.14
    erland
    -0.13
    POSITIVE LOGITS
    (L
    0.20
     LU
    0.17
    (LP
    0.17
    (LL
    0.17
    /L
    0.17
    =L
    0.17
     LS
    0.16
    (Log
    0.16
     LF
    0.16
     LM
    0.16
    Act Density 0.206%

    No Known Activations