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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations, such as cities and landmarks

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and entities, particularly in relation to sports and geography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )."
    -0.76
    ]."
    -0.74
    ).[
    -0.63
     meanwhile
    -0.61
    .'"
    -0.61
    .")
    -0.61
    '."
    -0.61
    )].
    -0.58
    ĵĺ
    -0.57
    anwhile
    -0.55
    POSITIVE LOGITS
    uin
    0.50
     GU
    0.44
     ancestor
    0.43
    owship
    0.43
     ITS
    0.42
     Heavenly
    0.42
     i
    0.41
    Firstly
    0.41
     AX
    0.41
     ORIG
    0.41
    Act Density 3.399%

    No Known Activations