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

    Neuronpedia

    INDEX
    Explanations

    phrases related to locations or places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oxide
    -0.72
    load
    -0.72
    ogram
    -0.70
    arians
    -0.69
    winning
    -0.67
    iam
    -0.67
    mg
    -0.67
    uty
    -0.66
    handedly
    -0.65
    rists
    -0.65
    POSITIVE LOGITS
     vicinity
    1.51
     midst
    1.41
     confines
    1.23
     meantime
    1.19
     attic
    1.12
     guise
    1.09
     basement
    1.07
     absence
    1.07
     halls
    1.04
     depths
    1.03
    Act Density 0.296%

    No Known Activations