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

    Neuronpedia

    INDEX
    Explanations

    dates, technical specifications, and proper nouns like names and locations

    oai_token-act-pair · gpt-3.5-turbo

    elements related to dates, times, and numerical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptions
    -0.75
    ãĥ¼ãĥ«
    -0.74
     bacter
    -0.72
    ancies
    -0.71
    ucc
    -0.68
     Bots
    -0.68
     Mercenary
    -0.68
    enegger
    -0.66
    berman
    -0.64
    onym
    -0.63
    POSITIVE LOGITS
    12
    1.05
    09
    0.97
    11
    0.93
    08
    0.88
    13
    0.86
     09
    0.86
     12
    0.85
    س
    0.84
     11
    0.81
    14
    0.80
    Act Density 0.398%

    No Known Activations