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

    Neuronpedia

    INDEX
    Explanations

    words associated with performance and tricks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.65
    leyball
    -0.63
    мум
    -0.62
     Seasons
    -0.57
     Thermostat
    -0.55
    rowsiness
    -0.54
     radios
    -0.53
     rake
    -0.53
     sickle
    -0.52
    Komple
    -0.52
    POSITIVE LOGITS
     stunts
    0.71
     incríveis
    0.67
     stunt
    0.64
     increíbles
    0.63
     acrob
    0.63
    >`;
    0.63
     IEnumerator
    0.59
     محفوظة
    0.59
    JNIEnv
    0.59
    LOAT
    0.58
    Act Density 0.124%

    No Known Activations