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

    Neuronpedia

    INDEX
    Explanations

    occurrences of phrases involving numerical ranges

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities, durations, or frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hels
    -0.75
     HIP
    -0.71
     Harvest
    -0.70
    ARA
    -0.69
    اÙĦ
    -0.68
    Bio
    -0.66
    PDATE
    -0.63
    RF
    -0.63
     Meier
    -0.63
    ãĤ©
    -0.62
    POSITIVE LOGITS
     apiece
    0.99
    undred
    0.91
    fif
    0.86
    lled
    0.85
    doms
    0.81
    ousand
    0.77
    quarters
    0.76
    handled
    0.74
    pole
    0.73
    thirds
    0.72
    Act Density 0.264%

    No Known Activations