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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and structures in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -1.01
     itſelf
    -0.94
     pleaſure
    -0.88
    ſelves
    -0.85
     ſtate
    -0.85
    ſelf
    -0.84
     fevere
    -0.84
    neſs
    -0.84
     purpoſe
    -0.82
     himſelf
    -0.81
    POSITIVE LOGITS
     
    0.59
     J
    0.49
     Pre
    0.48
    alada
    0.47
     Real
    0.47
    itson
    0.45
    msgid
    0.45
    BeginContext
    0.44
    enderror
    0.43
     Del
    0.43
    Act Density 0.070%

    No Known Activations