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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "at" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fold
    -0.16
    anj
    -0.15
     Merchant
    -0.15
    aus
    -0.15
    oi
    -0.15
    inth
    -0.15
    CO
    -0.15
    ham
    -0.15
    ives
    -0.15
    rawn
    -0.14
    POSITIVE LOGITS
     rede
    0.15
     opport
    0.15
    rlen
    0.15
    pios
    0.15
    ylko
    0.15
    ceptar
    0.14
    iyan
    0.14
    hiba
    0.14
    ëł¹
    0.14
    cth
    0.14
    Act Density 0.120%

    No Known Activations