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

    Neuronpedia

    INDEX
    Explanations

    references to the rear of vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raph
    -0.16
    [$_
    -0.15
    _ASSUME
    -0.14
    STD
    -0.14
    rowse
    -0.13
    æĬ±
    -0.13
    /=
    -0.13
    _PIPELINE
    -0.13
    ecurity
    -0.13
     forehead
    -0.13
    POSITIVE LOGITS
    ward
    0.18
    -most
    0.18
    most
    0.17
    /back
    0.17
    wards
    0.16
    WARD
    0.15
    -only
    0.15
    ará
    0.14
    ersh
    0.14
    ɵ
    0.14
    Act Density 0.031%

    No Known Activations