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

    Neuronpedia

    INDEX
    Explanations

    Spanish names and related terms

    oai_token-act-pair · gpt-3.5-turbo

    the mention of a specific author and related names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llan
    -0.86
    aug
    -0.84
    cone
    -0.81
    berra
    -0.77
    ayson
    -0.75
     Pigs
    -0.73
    ugg
    -0.73
    worm
    -0.73
    pox
    -0.73
    zees
    -0.73
    POSITIVE LOGITS
     Bundesliga
    0.70
    ãĥ¤
    0.69
    agonist
    0.69
     Tanz
    0.68
    ioxid
    0.67
     Yose
    0.67
    ++++++++
    0.66
    ãĥ¯ãĥ³
    0.65
     Bundes
    0.65
    Īè
    0.65
    Act Density 0.024%

    No Known Activations