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

    Neuronpedia

    INDEX
    Explanations

    specific keywords, possibly related to technical topics or computer programming

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "The" at the beginning of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poke
    -0.71
    eno
    -0.67
    ito
    -0.63
    ����
    -0.63
    ement
    -0.62
    acea
    -0.62
    asonic
    -0.59
    gpu
    -0.59
    actory
    -0.58
    dding
    -0.58
    POSITIVE LOGITS
    oret
    1.38
    resa
    1.12
    odore
    1.04
     latter
    0.99
     downside
    0.97
    ories
    0.96
     simplest
    0.96
    nce
    0.89
     biggest
    0.88
    sis
    0.88
    Act Density 0.485%

    No Known Activations