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

    Neuronpedia

    INDEX
    Explanations

    phrases related to locations or place names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "den"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EH
    -0.63
    EED
    -0.63
    ROM
    -0.61
     behav
    -0.61
     Affect
    -0.61
     MPG
    -0.60
     overdue
    -0.59
     dys
    -0.59
    sit
    -0.59
    accompan
    -0.59
    POSITIVE LOGITS
    ning
    1.02
    heim
    1.00
    unciation
    0.99
    wald
    0.99
    den
    0.98
    izens
    0.97
    unci
    0.96
    omination
    0.90
    ving
    0.90
    omin
    0.90
    Act Density 0.005%

    No Known Activations