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

    Neuronpedia

    INDEX
    Explanations

    mentions of impressive achievements or remarkable accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe significant accomplishments or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srf
    -0.76
     iod
    -0.70
     Leilan
    -0.68
     Dot
    -0.67
     Galile
    -0.66
     propell
    -0.66
     Basin
    -0.65
    holm
    -0.65
     contracting
    -0.64
    iant
    -0.64
    POSITIVE LOGITS
    hered
    1.96
     feat
    1.02
     feats
    0.91
    icles
    0.91
    icle
    0.88
    hest
    0.85
    icular
    0.84
    hing
    0.80
    ree
    0.80
    chers
    0.80
    Act Density 0.012%

    No Known Activations