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

    Neuronpedia

    INDEX
    Explanations

    affirmative and negative responses in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.49
    >`;
    -0.48
     TAMBIÉN
    -0.46
    enumi
    -0.44
    "];
    -0.44
     itſelf
    -0.43
     Alamos
    -0.43
    :+:
    -0.43
     alfo
    -0.43
     AppDelegate
    -0.43
    POSITIVE LOGITS
     GenerationType
    0.68
    ropoda
    0.67
    rrggbb
    0.65
     spéciaux
    0.64
    siella
    0.64
     mères
    0.64
    جغرافيا
    0.63
     كومونز
    0.62
     kropp
    0.61
     pères
    0.60
    Act Density 0.191%

    No Known Activations