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

    Neuronpedia

    INDEX
    Explanations

    affirmative and negative responses or expressions of agreement and disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AlterField
    -0.59
    ();*/
    -0.57
    /');
    -0.57
     []:
    -0.55
    )<\
    -0.54
    ardians
    -0.53
    /***/
    -0.53
    )}=
    -0.53
    "]();
    -0.50
    inflate
    -0.49
    POSITIVE LOGITS
    Yes
    0.92
     Yes
    0.87
    yes
    0.82
     yes
    0.79
    YES
    0.75
     YES
    0.74
    Sì
    0.68
    Yess
    0.67
    YesNo
    0.67
     riuscito
    0.65
    Act Density 0.397%

    No Known Activations