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

    Neuronpedia

    INDEX
    Explanations

    phrases related to someone or something becoming notable or significant

    oai_token-act-pair · gpt-3.5-turbo

    articles and descriptors related to significant entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     goodness
    -0.71
    abilities
    -0.69
    !/
    -0.69
    erity
    -0.67
    agree
    -0.66
    packs
    -0.65
    icity
    -0.65
    panel
    -0.64
    books
    -0.62
    achu
    -0.62
    POSITIVE LOGITS
     scapego
    0.84
     fodder
    0.84
    irl
    0.77
     permanent
    0.77
     martyr
    0.76
     unwitting
    0.75
     casualty
    0.73
     focal
    0.73
    hemer
    0.73
     unstoppable
    0.72
    Act Density 0.128%

    No Known Activations