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

    Neuronpedia

    INDEX
    Explanations

    instances of the abbreviation "US"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "US" and "UK" within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzle
    -0.81
    issance
    -0.75
    idates
    -0.70
    âĶĢâĶĢ
    -0.68
    idate
    -0.67
    ttes
    -0.66
    oscope
    -0.65
    rette
    -0.65
    lihood
    -0.65
    ezvous
    -0.63
    POSITIVE LOGITS
    ADA
    1.04
    AF
    0.97
    AAF
    0.96
    GI
    0.94
    GS
    0.94
    AGE
    0.91
    NI
    0.90
    GA
    0.89
    AA
    0.88
    BC
    0.86
    Act Density 0.045%

    No Known Activations