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

    Neuronpedia

    INDEX
    Explanations

    references to animals or camouflage-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imers
    -0.18
    999
    -0.15
    yles
    -0.15
    麦
    -0.14
    afa
    -0.14
    ĥ½
    -0.13
    onor
    -0.13
    лоÑĩ
    -0.13
    SystemService
    -0.13
    bles
    -0.13
    POSITIVE LOGITS
    -like
    0.19
     optional
    0.17
     Pregn
    0.15
    aurus
    0.15
    ĵ
    0.15
    (es
    0.14
    жд
    0.14
    /stdc
    0.14
    uze
    0.14
    ATRIX
    0.13
    Act Density 0.109%

    No Known Activations