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

    Neuronpedia

    INDEX
    Explanations

    dates expressed in closed ranges (e.g., "2015-16")

    oai_token-act-pair · gpt-3.5-turbo

    references to sports seasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.67
     wig
    -0.65
    aptop
    -0.63
    ongh
    -0.61
    eton
    -0.60
    onyms
    -0.59
     dup
    -0.58
     Judah
    -0.58
     herself
    -0.58
     yourself
    -0.57
    POSITIVE LOGITS
     Ramadan
    0.87
     onwards
    0.79
    BuyableInstoreAndOnline
    0.72
     Eid
    0.72
     guiActiveUnfocused
    0.67
    lymp
    0.67
    EVA
    0.66
    glas
    0.65
    bia
    0.63
     slump
    0.62
    Act Density 0.346%

    No Known Activations