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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific features, requirements, and options in relation to software or technology

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ºC
    -0.78
     marte
    -0.67
     mercen
    -0.66
     Valentín
    -0.66
     ordina
    -0.64
     vost
    -0.63
     poiv
    -0.63
     chng
    -0.63
    nó
    -0.62
     asado
    -0.62
    POSITIVE LOGITS
     can
    0.72
     should
    0.69
     needn
    0.66
     will
    0.61
     must
    0.61
     impra
    0.61
     mustn
    0.61
     could
    0.60
     may
    0.59
     apprehen
    0.58
    Act Density 0.315%

    No Known Activations