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

    Neuronpedia

    INDEX
    Explanations

    names of geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    specific geographical locations or place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estyles
    -0.67
    adobe
    -0.67
    aci
    -0.65
    acci
    -0.63
    ãĥĩãĤ£
    -0.60
    sych
    -0.58
    othe
    -0.56
    ãĥ£
    -0.56
    omsky
    -0.56
    mble
    -0.55
    POSITIVE LOGITS
    's
    0.77
     itself
    0.70
    MSN
    0.59
    SON
    0.59
     Stadium
    0.58
    âĢ²
    0.57
     Airlines
    0.57
     Citadel
    0.57
     counterpart
    0.56
     TAMADRA
    0.56
    Act Density 0.460%

    No Known Activations