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

    Neuronpedia

    INDEX
    Explanations

    references to memorable or significant events happening only once in a lifetime

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "time."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udeb
    -0.81
    oras
    -0.79
    ochet
    -0.77
    ggles
    -0.76
    haps
    -0.73
    ific
    -0.70
    artisan
    -0.69
    Tags
    -0.68
    MAT
    -0.67
    ī
    -0.67
    POSITIVE LOGITS
    theless
    1.09
    etime
    1.08
     Pradesh
    0.81
     msec
    0.71
    nown
    0.71
    etheless
    0.70
     iod
    0.68
     broadcasts
    0.66
     ILCS
    0.65
     Frieza
    0.64
    Act Density 0.008%

    No Known Activations