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

    Neuronpedia

    INDEX
    Explanations

    words that imply positivity or affirmations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.89
    homonymie
    -0.86
     disambiguazione
    -0.85
    ⓘ
    -0.84
    rungsseite
    -0.75
    WithIOException
    -0.72
     nakalista
    -0.71
     ujednoznacz
    -0.71
     الحره
    -0.65
    -0.65
    POSITIVE LOGITS
    assertRaises
    0.58
    DebuggerNonUser
    0.52
     onAnimation
    0.50
    海道
    0.49
     oeufs
    0.45
     beeind
    0.45
     sockaddr
    0.44
    enumii
    0.43
     Кубка
    0.43
    ví
    0.43
    Act Density 0.003%

    No Known Activations