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

    Neuronpedia

    INDEX
    Explanations

    numbers related to dates

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the number "26" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Weaver
    -0.77
    ysc
    -0.76
    ETF
    -0.75
    etz
    -0.74
    sticks
    -0.68
    etr
    -0.66
     Lantern
    -0.65
    AW
    -0.64
    ets
    -0.63
     welf
    -0.63
    POSITIVE LOGITS
     26
    2.36
    26
    1.72
     46
    1.57
     266
    1.50
     66
    1.47
     27
    1.44
     36
    1.41
     31
    1.40
     06
    1.39
     126
    1.38
    Act Density 0.064%

    No Known Activations