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

    Neuronpedia

    INDEX
    Explanations

    affirmative statements or expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bitte
    -0.52
    ссмо
    -0.47
    ftc
    -0.45
    Skocz
    -0.44
    tvguidetime
    -0.44
     potete
    -0.43
    __(
    -0.43
    goku
    -0.43
    foro
    -0.42
     dernière
    -0.41
    POSITIVE LOGITS
    Indeed
    0.95
     indeed
    0.90
     Indeed
    0.89
    的确
    0.85
    indeed
    0.84
     yes
    0.83
     Yes
    0.83
     inderdaad
    0.81
     agree
    0.81
     Agree
    0.79
    Act Density 0.254%

    No Known Activations