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

    Neuronpedia

    INDEX
    Explanations

    words related to questions or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     morire
    -0.72
     isolato
    -0.63
     affez
    -0.59
     fatica
    -0.59
     titolata
    -0.58
     חיצוניים
    -0.56
     giusti
    -0.55
     scattata
    -0.54
    enumii
    -0.54
     conseguenza
    -0.54
    POSITIVE LOGITS
     Il
    0.80
     È
    0.77
     La
    0.77
     Nel
    0.76
     Gli
    0.72
     Nell
    0.71
     Sono
    0.71
     Si
    0.69
    Nel
    0.69
     Viene
    0.69
    Act Density 0.017%

    No Known Activations