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

    Neuronpedia

    INDEX
    Explanations

    expressions of thought or belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portály
    -0.80
    ης
    -0.61
     Cuerpo
    -0.55
    ]+$
    -0.55
    ładka
    -0.54
     akal
    -0.53
    };*/
    -0.52
    Więcej
    -0.52
     alcun
    -0.51
     Civil
    -0.51
    POSITIVE LOGITS
     think
    0.88
    луй
    0.80
     probably
    0.77
    Probably
    0.77
    matchCondition
    0.76
     chyba
    0.76
     glaube
    0.75
    ungkin
    0.74
    Certainly
    0.72
    تقاوى
    0.70
    Act Density 0.090%

    No Known Activations