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

    Neuronpedia

    INDEX
    Explanations

    relationships and interactions among characters or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighb
    -0.17
    hest
    -0.17
     акÑĤи
    -0.17
    udur
    -0.15
    ãĥ¼ãĥĬ
    -0.15
    æĪ·
    -0.15
    blade
    -0.15
    pt
    -0.14
    aight
    -0.14
    OOD
    -0.14
    POSITIVE LOGITS
     recip
    0.21
     vs
    0.15
     being
    0.15
     âĨĶ
    0.14
    _vs
    0.14
     while
    0.14
     versus
    0.13
     Ari
    0.13
    BN
    0.13
    props
    0.13
    Act Density 0.296%

    No Known Activations