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

    Neuronpedia

    INDEX
    Explanations

    proper names and entities related to journalism and news coverage

    oai_token-act-pair · gpt-3.5-turbo

    the names of individuals and references to organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srf
    -0.91
    icion
    -0.81
    */(
    -0.77
    ļ
    -0.72
    ay
    -0.70
    lete
    -0.69
    cknow
    -0.69
    ibel
    -0.68
    umbered
    -0.68
    son
    -0.68
    POSITIVE LOGITS
    ione
    0.71
    ertodd
    0.69
    enegger
    0.67
    inian
    0.66
     Rept
    0.66
     Malfoy
    0.65
     Lakes
    0.64
     Ding
    0.64
     noodles
    0.64
     Tigers
    0.63
    Act Density 0.107%

    No Known Activations