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

    Neuronpedia

    INDEX
    Explanations

    phrases related to determining or assessing specific information or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.92
     “
    -0.79
     Ha
    -0.75
    ha
    -0.68
     alto
    -0.67
    <strong>
    -0.66
     I
    -0.66
     go
    -0.65
     H
    -0.65
    1
    -0.65
    POSITIVE LOGITS
     myſelf
    1.43
     Efq
    1.42
     itſelf
    1.41
     purpoſe
    1.35
     Reſ
    1.34
     Majefty
    1.34
    Determine
    1.29
    parsedMessage
    1.28
     Eſ
    1.28
     determinations
    1.28
    Act Density 0.046%

    No Known Activations