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

    Neuronpedia

    INDEX
    Explanations

    references to news media outlets and associated content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èįī
    -0.17
    .arc
    -0.17
    akis
    -0.16
    ngine
    -0.16
     arc
    -0.15
    abant
    -0.15
     mdl
    -0.15
     Arc
    -0.15
    úa
    -0.14
    ropa
    -0.14
    POSITIVE LOGITS
     Fox
    0.28
    Fox
    0.27
     FOX
    0.23
     fox
    0.22
    FOX
    0.21
    fox
    0.20
     Fo
    0.19
    çĭIJ
    0.17
    Fo
    0.17
    _HW
    0.15
    Act Density 0.016%

    No Known Activations