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

    Neuronpedia

    INDEX
    Explanations

    rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¹
    -2.81
    ¯
    -2.44
    Ń
    -2.43
    ®
    -2.42
    ¤
    -2.41
    ¸
    -2.39
    ³
    -2.36
    -2.36
    ½
    -2.32
    ¼
    -2.31
    POSITIVE LOGITS
    ioned
    1.77
    oons
    1.66
    oon
    1.55
    chen
    1.53
    outh
    1.50
    ourt
    1.39
    omology
    1.37
    eros
    1.35
    ionate
    1.34
    sed
    1.33
    Act Density 0.005%

    No Known Activations