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

    Neuronpedia

    INDEX
    Explanations

    variables or expressions referring to mathematical or computational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.90
     Beſ
    -0.71
     ſeveral
    -0.71
    ()].
    -0.70
     Conſ
    -0.69
    neſs
    -0.69
     themſelves
    -0.68
     myſelf
    -0.68
     Anſ
    -0.67
     Diſ
    -0.67
    POSITIVE LOGITS
     x
    1.42
     X
    1.29
    X
    1.13
    x
    1.11
     getX
    1.07
    getX
    1.05
    xH
    0.97
    ylem
    0.93
    Xylene
    0.90
     Xander
    0.90
    Act Density 0.269%

    No Known Activations