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

    Neuronpedia

    INDEX
    Explanations

    references to input and output variables in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     morire
    -0.82
    antaranya
    -0.78
     newBuilder
    -0.77
     alberi
    -0.75
     secoli
    -0.74
     antaranya
    -0.73
     automatiques
    -0.72
    #
    -0.72
     defStyle
    -0.72
     gioielli
    -0.71
    POSITIVE LOGITS
     input
    3.37
     Input
    3.00
    input
    2.92
    Input
    2.79
     INPUT
    2.79
     inputs
    2.74
     Inputs
    2.51
    INPUT
    2.50
    inputs
    2.15
    Inputs
    2.15
    Act Density 0.093%

    No Known Activations