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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "whatever" and phrases indicating a lack of evidence or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "]];
    -0.84
    "]').
    -0.83
    "]),
    -0.79
    ()));
    -0.79
    "]);
    -0.79
    `).
    -0.78
    "]/
    -0.77
    ")));
    -0.77
    ")->
    -0.76
    "));
    -0.75
    POSITIVE LOGITS
     galore
    0.80
     تانيه
    0.67
     demografica
    0.65
    EDEFAULT
    0.65
    ROIT
    0.62
    DoubleQuotes
    0.61
     الحره
    0.60
     viceversa
    0.60
    engkapnya
    0.60
     Unito
    0.59
    Act Density 0.233%

    No Known Activations