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

    Neuronpedia

    INDEX
    Explanations

    various forms of words related to quality or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dụ
    -0.56
     Gers
    -0.52
    ciaal
    -0.49
    рое
    -0.47
    chid
    -0.47
    ))/(
    -0.46
    کار
    -0.46
    ilak
    -0.45
     recent
    -0.45
     peng
    -0.45
    POSITIVE LOGITS
    ality
    1.13
    ALITY
    1.06
    idad
    0.98
    alities
    0.97
    ITY
    0.96
    uality
    0.94
    idade
    0.91
    ArgsConstructor
    0.90
    ity
    0.90
     مرئيه
    0.89
    Act Density 0.312%

    No Known Activations