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

    Neuronpedia

    INDEX
    Explanations

    references to the authors' proposals and their involvement in research or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃs
    -0.18
    las
    -0.15
    ros
    -0.14
    é¦
    -0.13
     Rosen
    -0.13
     Tep
    -0.13
    ิà¸Ī
    -0.13
    jer
    -0.13
    çĤİ
    -0.13
    fac
    -0.13
    POSITIVE LOGITS
    ahren
    0.15
    loth
    0.15
    agh
    0.14
    olation
    0.14
    --------------------------------------------------------------------------↵
    0.14
     ong
    0.14
    iggers
    0.14
    atorium
    0.13
    dish
    0.13
    peria
    0.13
    Act Density 0.057%

    No Known Activations