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

    Neuronpedia

    INDEX
    Explanations

    references to membership and members in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ux
    -0.18
    ilt
    -0.17
    uto
    -0.16
    (es
    -0.16
    /Math
    -0.15
     Äijá»Ļ
    -0.15
     Morm
    -0.14
    lear
    -0.14
     Fighters
    -0.14
    ftware
    -0.14
    POSITIVE LOGITS
    hips
    0.30
    hip
    0.24
    ikan
    0.24
    chaft
    0.21
    ìĭŃ
    0.20
    ìī
    0.17
    hap
    0.17
    AccessException
    0.16
    atical
    0.16
    HIP
    0.15
    Act Density 0.040%

    No Known Activations