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

    Neuronpedia

    INDEX
    Explanations

    non-zero numeric values or indicators of quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stateProvider
    -0.90
    Portale
    -0.89
    تقاوى
    -0.86
     Wikimedijinoj
    -0.85
    Personensuche
    -0.85
    RetentionPolicy
    -0.85
    didSet
    -0.82
    mybatisplus
    -0.81
    UserScript
    -0.81
     لينك
    -0.78
    POSITIVE LOGITS
    <eos>
    0.69
    ↵
    0.58
    </strong>
    0.53
    </em>
    0.53
    z
    0.49
    etc
    0.49
    to
    0.47
    ul
    0.42
    fi
    0.41
    }$-
    0.40
    Act Density 0.122%

    No Known Activations