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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    dates formatted as "Oct [number]"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hots
    -0.78
    Reviewer
    -0.76
    adder
    -0.71
    istics
    -0.69
    edIn
    -0.67
     NIC
    -0.66
    footed
    -0.65
     Legion
    -0.65
    éĹĺ
    -0.65
     mad
    -0.65
    POSITIVE LOGITS
    opus
    1.19
    avia
    0.99
    av
    0.91
    isco
    0.89
    Oct
    0.89
    omore
    0.89
    Aug
    0.87
    ú
    0.86
    agonal
    0.85
    issa
    0.85
    Act Density 0.014%

    No Known Activations