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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical formulas and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.85
     myſelf
    -0.82
     Theſe
    -0.75
     pleaſure
    -0.73
     Beſ
    -0.72
     itſelf
    -0.69
     fubject
    -0.69
     ſch
    -0.68
     themſelves
    -0.67
     anſ
    -0.67
    POSITIVE LOGITS
     formula
    0.71
     portal
    0.66
     Portal
    0.59
     FORMULA
    0.58
     Formula
    0.56
     partnership
    0.56
     Port
    0.56
    formula
    0.56
     line
    0.52
     signal
    0.52
    Act Density 0.490%

    No Known Activations