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

    Neuronpedia

    INDEX
    Explanations

    mentions of tasks or actions that are accomplished or achieved

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "by" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppa
    -0.77
    bard
    -0.67
    SPONSORED
    -0.67
    emo
    -0.66
    stakes
    -0.66
    ahead
    -0.66
    Pict
    -0.66
    thal
    -0.66
    meat
    -0.66
    aser
    -0.65
    POSITIVE LOGITS
     virtue
    1.13
    products
    0.97
     multiplying
    0.93
     means
    0.76
     utilizing
    0.74
     combining
    0.73
    catch
    0.72
     accident
    0.72
     fiat
    0.71
     mistake
    0.70
    Act Density 0.144%

    No Known Activations