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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases that connect ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /ion
    -0.15
    ersh
    -0.15
    (GLFW
    -0.14
    áš
    -0.14
    cke
    -0.13
     Signature
    -0.13
    [cell
    -0.13
    riel
    -0.13
    zek
    -0.13
    ýn
    -0.13
    POSITIVE LOGITS
    odash
    0.16
    udget
    0.15
    ause
    0.15
    antar
    0.14
    esar
    0.14
    620
    0.14
    lum
    0.14
    arg
    0.14
    erais
    0.14
    Į
    0.14
    Act Density 0.690%

    No Known Activations