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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of" in various contexts, indicating a pattern related to specifying locations or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.84
     reperto
    -0.73
    iership
    -0.70
    âĹ¼
    -0.69
    */(
    -0.69
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.67
     dictate
    -0.66
    <?
    -0.66
     ceilings
    -0.66
     certs
    -0.66
    POSITIVE LOGITS
     Normandy
    0.78
     Alb
    0.77
     Nev
    0.77
     Dover
    0.77
     Trinidad
    0.73
     Tir
    0.71
     Tripoli
    0.70
     Avalon
    0.70
     Albion
    0.69
     La
    0.69
    Act Density 0.056%

    No Known Activations