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

    Neuronpedia

    INDEX
    Explanations

    names and references related to authors and academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.72
    IVEREF
    -0.69
     himſelf
    -0.68
    andExpect
    -0.67
    性和
    -0.67
     Reſ
    -0.67
     Beſ
    -0.67
     Theſe
    -0.65
     Inſ
    -0.65
     itſelf
    -0.64
    POSITIVE LOGITS
     CWE
    0.51
    </em>
    0.48
     atencion
    0.43
     */
    0.41
    XmlAccessType
    0.40
    providedIn
    0.40
    __":
    0.39
    </h3>
    0.39
    ↵↵
    0.39
    macht
    0.39
    Act Density 0.250%

    No Known Activations