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

    Neuronpedia

    INDEX
    Explanations

    proper names and surnames in documents

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ishers
    -0.74
     canopy
    -0.72
    fty
    -0.67
    IRD
    -0.67
    sonian
    -0.66
    ISS
    -0.65
    fman
    -0.62
    READ
    -0.61
     Kitt
    -0.61
    ften
    -0.60
    POSITIVE LOGITS
    alez
    0.96
    hou
    0.95
    rez
    0.92
    ombie
    0.90
    uala
    0.87
    eta
    0.86
    quez
    0.83
    hi
    0.83
    etta
    0.81
    terday
    0.81
    Act Density 0.029%

    No Known Activations