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

    Neuronpedia

    INDEX
    Explanations

    words related to conflict or opposition

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "availability."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOAD
    -0.75
    ãĥ³ãĤ¸
    -0.73
     fracturing
    -0.68
    FORE
    -0.68
    Else
    -0.68
    TABLE
    -0.67
    FINE
    -0.66
    FORMATION
    -0.65
    hyde
    -0.63
     towels
    -0.63
    POSITIVE LOGITS
    iew
    1.13
    atars
    1.13
    ial
    1.02
    ionics
    1.00
    ille
    0.99
    oir
    0.98
    iste
    0.96
    ials
    0.95
    ril
    0.95
    iator
    0.94
    Act Density 0.007%

    No Known Activations