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

    Neuronpedia

    INDEX
    Explanations

    phrases related to experienced individuals or their demeanor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ffilmiau
    -0.75
    évaluateur
    -0.67
     odkazy
    -0.53
    ]=="
    -0.49
    kusi
    -0.49
     ویکی‌پدی
    -0.47
    üş
    -0.47
    ьажоргаш
    -0.45
    Parabéns
    -0.45
    Források
    -0.45
    POSITIVE LOGITS
     reluctant
    0.65
     unwillingness
    0.57
    writeFieldEnd
    0.57
    crombie
    0.56
     reluctance
    0.54
     review
    0.53
    Sucesor
    0.52
    sizeCache
    0.52
    sedia
    0.51
     negó
    0.51
    Act Density 0.400%

    No Known Activations