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

    Neuronpedia

    INDEX
    Explanations

    dates and events mentioned in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    dates or specific time-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wong
    -0.80
     KP
    -0.73
    ierrez
    -0.65
     LAPD
    -0.64
    Case
    -0.63
     shorth
    -0.63
    cases
    -0.62
    gu
    -0.61
     Gaw
    -0.61
     Chilean
    -0.61
    POSITIVE LOGITS
     looting
    0.74
    elf
    0.73
     Restoration
    0.69
    tones
    0.69
     FANTASY
    0.67
     leveling
    0.66
    rift
    0.66
    iasis
    0.64
    tered
    0.64
     mete
    0.64
    Act Density 0.000%

    No Known Activations