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

    Neuronpedia

    INDEX
    Explanations

    names of individuals ending in 'er'

    oai_token-act-pair · gpt-3.5-turbo

    names of people or identifiable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACTED
    -0.69
     envy
    -0.64
     territorial
    -0.59
    姫
    -0.59
    BOOK
    -0.57
    ITED
    -0.57
    merce
    -0.57
    CRIP
    -0.56
     rook
    -0.56
    çķ
    -0.56
    POSITIVE LOGITS
    enberg
    0.88
    inger
    0.85
    ney
    0.83
    eman
    0.82
    nick
    0.81
    zel
    0.79
    ley
    0.79
    olla
    0.78
    iger
    0.77
    cko
    0.77
    Act Density 0.243%

    No Known Activations