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

    Neuronpedia

    INDEX
    Explanations

    function calls and initializations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '
    -0.56
     H
    -0.53
     corre
    -0.53
     O
    -0.51
     c
    -0.51
     ‘
    -0.51
     "
    -0.50
     ot
    -0.50
     l
    -0.49
     h
    -0.49
    POSITIVE LOGITS
     pleaſure
    1.08
     ſtate
    0.93
     Efq
    0.93
     myſelf
    0.92
    Geplaatst
    0.92
     houſe
    0.90
     purpoſe
    0.89
     uſe
    0.86
    Tikang
    0.86
     fubject
    0.84
    Act Density 0.054%

    No Known Activations