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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating qualifications or conditions frequently linked to the word "least."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dden
    -0.17
    filer
    -0.15
    ast
    -0.14
    PF
    -0.14
    er
    -0.14
    imiter
    -0.14
    yal
    -0.14
     apenas
    -0.14
    ock
    -0.13
     Gord
    -0.13
    POSITIVE LOGITS
    urret
    0.18
    itus
    0.18
     partial
    0.15
    s
    0.15
    sÃŃ
    0.15
    utom
    0.14
    343
    0.14
     crow
    0.14
    itudes
    0.14
    rollo
    0.14
    Act Density 0.024%

    No Known Activations