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

    Neuronpedia

    INDEX
    Explanations

    references to membership and membership-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ux
    -0.17
     Äijá»Ļ
    -0.17
    ilt
    -0.16
    setter
    -0.15
    aming
    -0.15
    lear
    -0.15
    çĽĸ
    -0.15
    (es
    -0.15
    ãģªãģı
    -0.15
    /Math
    -0.14
    POSITIVE LOGITS
    hips
    0.28
    hip
    0.23
    ikan
    0.23
    chaft
    0.20
    (Member
    0.18
    ìĭŃ
    0.17
    AccessException
    0.17
    ìī
    0.16
    hap
    0.15
    /member
    0.15
    Act Density 0.042%

    No Known Activations