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

    Neuronpedia

    INDEX
    Explanations

    references to structured or mathematical notations in scientific text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -0.92
     himſelf
    -0.88
     للمعارف
    -0.88
     Theſe
    -0.88
     myſelf
    -0.85
     themſelves
    -0.84
     auffi
    -0.82
     Monfieur
    -0.82
     resourceCulture
    -0.81
     pleaſure
    -0.81
    POSITIVE LOGITS
    guchi
    0.71
    gdx
    0.65
     co
    0.59
     Wilber
    0.57
     figure
    0.56
    overset
    0.56
     cal
    0.56
    La
    0.56
     la
    0.56
     La
    0.55
    Act Density 0.071%

    No Known Activations