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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.72
     Tao
    -0.72
    chens
    -0.68
    race
    -0.67
     Commando
    -0.65
    nda
    -0.63
    ao
    -0.62
    Irish
    -0.61
    agi
    -0.61
    pora
    -0.61
    POSITIVE LOGITS
    ruary
    0.87
    enthal
    0.81
    esse
    0.77
    idays
    0.73
    oult
    0.72
    istic
    0.70
    theless
    0.69
    enberg
    0.67
    iflower
    0.65
    ickers
    0.65
    Act Density 0.032%

    No Known Activations