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

    Neuronpedia

    INDEX
    Explanations

    person names, particularly last names

    oai_token-act-pair · gpt-3.5-turbo

    proper names and references to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Poles
    -0.76
     Lump
    -0.74
    Balt
    -0.74
     Siberian
    -0.70
    pole
    -0.70
    Var
    -0.69
    ãĥª
    -0.69
    Bir
    -0.68
    é£
    -0.66
    istically
    -0.66
    POSITIVE LOGITS
    endez
    1.32
    vous
    1.04
    afort
    0.90
    ktop
    0.84
    iasis
    0.82
    ese
    0.80
    enture
    0.79
    cano
    0.77
    ortium
    0.76
    aye
    0.75
    Act Density 0.011%

    No Known Activations