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

    Neuronpedia

    INDEX
    Explanations

    affirmative statements or confirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emer
    -0.17
    asley
    -0.17
    chas
    -0.15
    ont
    -0.15
    emoc
    -0.15
    amage
    -0.15
    ванов
    -0.14
    iko
    -0.14
     Hale
    -0.14
    stand
    -0.14
    POSITIVE LOGITS
    atty
    0.16
    arth
    0.16
    forth
    0.15
    orable
    0.15
    éĹ
    0.15
    γει
    0.15
     quant
    0.14
    ÑĢаÑħ
    0.14
    anton
    0.14
    leck
    0.14
    Act Density 0.047%

    No Known Activations