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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctions
    -0.15
     ifndef
    -0.15
    739
    -0.14
    İ
    -0.14
    RAP
    -0.14
    agate
    -0.14
    rap
    -0.14
    [#
    -0.14
    rag
    -0.14
     ticket
    -0.14
    POSITIVE LOGITS
    onto
    0.20
    raft
    0.16
    onso
    0.16
    ɵ
    0.15
     Sherman
    0.15
     Coat
    0.14
     CONTRIBUTORS
    0.14
     CreateMap
    0.14
    ModelError
    0.14
    paralleled
    0.13
    Act Density 0.125%

    No Known Activations