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

    Neuronpedia

    INDEX
    Explanations

    references to membership or affiliation with organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģªãģı
    -0.16
    ÏĢα
    -0.15
    ftware
    -0.14
    aming
    -0.14
    ilt
    -0.14
     Fighters
    -0.14
    ائد
    -0.14
    /free
    -0.14
     Morm
    -0.13
    çĽĸ
    -0.13
    POSITIVE LOGITS
    hips
    0.27
    ikan
    0.22
    hip
    0.21
    chaft
    0.18
    (Member
    0.18
    ìĭŃ
    0.17
    inded
    0.17
    èµĦæł¼
    0.16
    ìī
    0.16
    /member
    0.16
    Act Density 0.045%

    No Known Activations