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

    Neuronpedia

    INDEX
    Explanations

    foreign phrases or words

    oai_token-act-pair · gpt-3.5-turbo

    fragments or components of names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IUM
    -0.89
    DragonMagazine
    -0.88
    untled
    -0.72
    æ©
    -0.71
    Flash
    -0.71
    Reloaded
    -0.71
    Contract
    -0.69
    VILLE
    -0.68
    Tokens
    -0.67
    Bloom
    -0.66
    POSITIVE LOGITS
    ande
    0.86
     los
    0.80
     thou
    0.75
     este
    0.72
     ded
    0.68
    nih
    0.68
    otent
    0.68
     ay
    0.68
    unci
    0.67
     tu
    0.66
    Act Density 0.153%

    No Known Activations