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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a question or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ་་
    -1.04
     ―――――
    -0.96
     ſind
    -0.91
     ***/
    -0.89
     itſelf
    -0.85
     (\<
    -0.84
     Houſe
    -0.83
    Obrázky
    -0.82
     $_"
    -0.81
    XmlAccessorType
    -0.78
    POSITIVE LOGITS
    ...
    0.67
    ?
    0.62
    !
    0.59
    .
    0.59
     #
    0.58
     
    0.56
    …
    0.56
     I
    0.55
    </b>
    0.55
    ↵↵
    0.55
    Act Density 0.847%

    No Known Activations