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

    Neuronpedia

    INDEX
    Explanations

    expressions of preference or desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rib
    -0.15
    AKE
    -0.15
    830
    -0.14
    rible
    -0.14
    ser
    -0.14
    ropa
    -0.14
    enna
    -0.13
    re
    -0.13
    fi
    -0.13
    res
    -0.13
    POSITIVE LOGITS
    gow
    0.16
    .crm
    0.15
    ingers
    0.14
    idity
    0.14
    mente
    0.13
    ë©ĺ
    0.13
    ITERAL
    0.13
    existent
    0.13
    رÙĪÛĮ
    0.13
    lobal
    0.13
    Act Density 0.036%

    No Known Activations