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

    Neuronpedia

    INDEX
    Explanations

    numerical values presented in a specific format within text

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or figures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     padd
    -0.76
     elevation
    -0.71
     travers
    -0.70
     swallowing
    -0.68
     pastoral
    -0.68
     guarding
    -0.66
     brid
    -0.66
     railing
    -0.65
     expelled
    -0.64
     subord
    -0.64
    POSITIVE LOGITS
     SHARES
    0.97
     NCT
    0.80
    nd
    0.80
    ½
    0.79
    121
    0.79
    646
    0.79
    226
    0.78
    :{
    0.78
    rd
    0.77
    maxwell
    0.77
    Act Density 0.079%

    No Known Activations