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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Sam."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    steen
    -0.19
    itia
    -0.19
    ISTA
    -0.17
    geois
    -0.16
    eking
    -0.15
    illez
    -0.14
    eyen
    -0.14
    icz
    -0.14
    atitude
    -0.13
    IMITER
    -0.13
    POSITIVE LOGITS
    son
    0.27
    uel
    0.24
    plings
    0.21
    ual
    0.20
    urai
    0.20
    plers
    0.19
    plr
    0.19
    pras
    0.18
    uele
    0.18
    SON
    0.18
    Act Density 0.008%

    No Known Activations