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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¢ãĥ«
    -0.15
    дап
    -0.14
    ำ
    -0.14
    itty
    -0.14
    agt
    -0.14
    سÙĬÙĨ
    -0.14
    reed
    -0.13
     ux
    -0.13
    elmet
    -0.13
     omas
    -0.13
    POSITIVE LOGITS
    ìķ½
    0.15
    patial
    0.15
    iaz
    0.14
    μον
    0.14
    .si
    0.14
    edio
    0.14
    594
    0.14
     Byl
    0.14
    cn
    0.14
    523
    0.13
    Act Density 0.115%

    No Known Activations