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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and their interactions in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.94
     myſelf
    -0.88
     ſeveral
    -0.81
     themſelves
    -0.80
     himſelf
    -0.75
     Weih
    -0.75
    Tikang
    -0.74
     Anſ
    -0.74
    neſs
    -0.73
     ſever
    -0.73
    POSITIVE LOGITS
     x
    1.30
    x
    1.13
    xH
    1.03
    Zeneca
    0.84
     Bx
    0.82
     y
    0.81
    Jx
    0.79
    posx
    0.79
     gluon
    0.77
    tisgarh
    0.77
    Act Density 0.372%

    No Known Activations