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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to people or objects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itan
    -0.16
    autoload
    -0.16
    imus
    -0.15
     Bene
    -0.14
    sko
    -0.14
    BufferSize
    -0.14
    enta
    -0.14
    ÙħÙĪÙĦ
    -0.14
    override
    -0.14
     Ben
    -0.14
    POSITIVE LOGITS
    idor
    0.19
    idelberg
    0.17
    igli
    0.16
    bsites
    0.15
     Silk
    0.15
    ëĵľë¦¬
    0.15
    ooth
    0.15
    èļ
    0.14
     récup
    0.14
    een
    0.14
    Act Density 0.139%

    No Known Activations