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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by a form of the verb 'to be.'

    oai_token-act-pair · gpt-3.5-turbo

    statements of opinion or belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itta
    -0.68
    idth
    -0.62
    Major
    -0.62
    stellar
    -0.61
    catentry
    -0.58
     Credits
    -0.57
    ãĤ¢
    -0.57
     Atom
    -0.56
    restling
    -0.56
    hift
    -0.56
    POSITIVE LOGITS
    alian
    1.07
    chy
    1.04
    's
    0.98
     strengthens
    0.96
     hurts
    0.96
     happens
    0.95
     belongs
    0.95
     qualifies
    0.94
     mattered
    0.94
     wasn
    0.94
    Act Density 0.121%

    No Known Activations