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

    Neuronpedia

    INDEX
    Explanations

    keywords related to a specific geographical location, potentially referring to a town or specific place

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ond" within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mson
    -0.76
    jriwal
    -0.75
    kson
    -0.72
    CLE
    -0.71
    ttle
    -0.69
    ======
    -0.68
    glers
    -0.68
    BILITIES
    -0.65
     teasp
    -0.63
    plates
    -0.63
    POSITIVE LOGITS
    ragon
    1.11
    orf
    1.04
    ering
    1.02
    erer
    0.99
    iverse
    0.88
    erers
    0.86
    ered
    0.83
    isl
    0.82
    ers
    0.82
    iscover
    0.81
    Act Density 0.029%

    No Known Activations