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

    Neuronpedia

    INDEX
    Explanations

    terms related to scoring and points in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -stats
    -0.16
    kees
    -0.15
    ãĥ³ãĥĢ
    -0.14
    -tip
    -0.14
    argo
    -0.14
    erty
    -0.14
     Ire
    -0.14
    ptic
    -0.14
     Nom
    -0.13
    izo
    -0.13
    POSITIVE LOGITS
    awy
    0.15
    हर
    0.14
    izable
    0.14
    opr
    0.14
    prt
    0.14
     Kro
    0.14
    upert
    0.14
    à¥Ģस
    0.14
    logan
    0.13
    rift
    0.13
    Act Density 0.064%

    No Known Activations