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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or sequences within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     June
    -0.21
     Jun
    -0.18
    June
    -0.18
    Jun
    -0.17
    July
    -0.17
    ãĥ¼ãĥijãĥ¼
    -0.16
     Fourth
    -0.16
     Jul
    -0.15
     Juni
    -0.15
     July
    -0.15
    POSITIVE LOGITS
    8
    0.90
     eight
    0.84
    åħ«
    0.83
     Eight
    0.77
     åħ«
    0.74
    eight
    0.73
     August
    0.72
    -eight
    0.71
     Eighth
    0.69
    Eight
    0.69
    Act Density 0.351%

    No Known Activations