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

    Neuronpedia

    INDEX
    Explanations

    terms related to estimations and approximations of values or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oporosis
    -0.51
     identified
    -0.50
    </i>
    -0.50
    smith
    -0.50
    </b>
    -0.50
    мам
    -0.49
    UObject
    -0.49
    station
    -0.47
    schlag
    -0.46
    ness
    -0.46
    POSITIVE LOGITS
    timate
    0.90
     Roskov
    0.86
    Personensuche
    0.80
    IMATE
    0.80
     GenerationType
    0.78
     Himo
    0.72
     iſt
    0.71
    0.71
    ]")]
    0.69
    titleMargin
    0.68
    Act Density 0.133%

    No Known Activations