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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to specific individuals, such as "Petrov" followed by a number indicating the strength of the match

    oai_token-act-pair · gpt-3.5-turbo

    the name "Rov" or variations of it as a significant entity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grail
    -0.79
    cock
    -0.68
     Scots
    -0.67
     Scottish
    -0.67
    print
    -0.66
    IRD
    -0.65
     Jolly
    -0.64
    FACE
    -0.64
    POS
    -0.63
     Mercury
    -0.61
    POSITIVE LOGITS
    rov
    1.21
    irus
    1.06
    isions
    1.05
    incial
    1.04
    vernment
    0.94
    ania
    0.91
    itals
    0.90
    ideo
    0.90
    rolet
    0.89
    iev
    0.88
    Act Density 0.008%

    No Known Activations