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

    Neuronpedia

    INDEX
    Explanations

    names and personal information

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confir
    -0.85
     feasible
    -0.83
    ccording
    -0.78
     conclud
    -0.77
     disadvantages
    -0.76
    Reviewer
    -0.74
    INTER
    -0.74
     conflic
    -0.72
    CLASS
    -0.72
     classify
    -0.72
    POSITIVE LOGITS
     Zup
    1.07
     TBA
    1.06
     Nay
    1.06
     Mai
    1.04
     Zo
    1.03
     Jac
    1.03
     Yaz
    1.03
     Jos
    1.03
     Ke
    1.03
     Mae
    1.02
    Act Density 0.200%

    No Known Activations