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

    Neuronpedia

    INDEX
    Explanations

    names followed by a title "retired" in a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals who are retired

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iola
    -0.71
     Grimm
    -0.67
    ebus
    -0.65
     Hispan
    -0.63
     coord
    -0.63
     Rig
    -0.62
    owitz
    -0.62
    hran
    -0.61
     similarities
    -0.61
    arta
    -0.61
    POSITIVE LOGITS
     retiring
    0.88
     retire
    0.77
    uting
    0.75
    spective
    0.74
    rifice
    0.74
    dinand
    0.72
    unte
    0.72
    ret
    0.72
    utes
    0.70
    Veter
    0.70
    Act Density 0.017%

    No Known Activations