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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating types or forms of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <>",
    -0.52
    adpleegd
    -0.52
     recrutement
    -0.51
    참고
    -0.50
    IonicModule
    -0.50
     propOrder
    -0.46
    SuppressMessage
    -0.45
     Оно
    -0.45
     Fewer
    -0.45
     обращения
    -0.44
    POSITIVE LOGITS
     quelconque
    0.87
     irgende
    0.84
     irgendwie
    0.76
     irgend
    0.72
    somewhere
    0.71
    Either
    0.70
    medriver
    0.70
     valami
    0.70
    Somewhere
    0.69
    either
    0.68
    Act Density 0.324%

    No Known Activations