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

    Neuronpedia

    INDEX
    Explanations

    HTML attributes and their values in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.58
     Ber
    -0.50
     mit
    -0.48
     micro
    -0.48
    /");
    -0.48
     
    -0.48
     An
    -0.47
     CH
    -0.47
     About
    -0.46
     pat
    -0.44
    POSITIVE LOGITS
     Monfieur
    0.90
     myſelf
    0.88
     Cæsar
    0.84
     Majefty
    0.83
     sarees
    0.82
     HttpNotFound
    0.80
     Efq
    0.79
     himſelf
    0.78
     Shale
    0.78
     becauſe
    0.78
    Act Density 0.178%

    No Known Activations