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

    Neuronpedia

    INDEX
    Explanations

    mentions of new additions or enhancements

    oai_token-act-pair · gpt-3.5-turbo

    references to new additions or improvements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zees
    -0.72
    rior
    -0.72
    zh
    -0.71
    zee
    -0.69
    rpm
    -0.66
    raz
    -0.65
    rolled
    -0.64
    bis
    -0.63
    yah
    -0.63
    robe
    -0.61
    POSITIVE LOGITS
    endum
    0.96
    xual
    0.84
    xon
    0.79
    ition
    0.79
    verted
    0.78
     thereto
    0.76
     Flavoring
    0.75
     insult
    0.71
    itives
    0.70
    itious
    0.68
    Act Density 0.038%

    No Known Activations