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

    Neuronpedia

    INDEX
    Explanations

    concepts related to conditions and effects in scientific discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.85
    itself
    -0.74
     its
    -0.72
     которое
    -0.63
     яке
    -0.63
     Its
    -0.60
    Its
    -0.59
     Itself
    -0.54
     оно
    -0.54
    its
    -0.53
    POSITIVE LOGITS
     themselves
    0.90
    themselves
    0.80
     amelyek
    0.76
     jotka
    0.69
     cherchés
    0.65
     illustrationer
    0.63
     eivät
    0.60
     leerlingen
    0.59
     abstrait
    0.58
     generalizations
    0.57
    Act Density 3.397%

    No Known Activations