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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant advancements or progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant advancements or improvements, particularly those described as "leaps."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essee
    -0.95
    Interstitial
    -0.84
    urally
    -0.70
    ividually
    -0.69
     corrid
    -0.68
    entary
    -0.67
    gel
    -0.65
    idad
    -0.63
    ãĤ±
    -0.63
     Beware
    -0.62
    POSITIVE LOGITS
    frog
    1.15
    olate
    0.81
    rers
    0.79
    ering
    0.78
     leaps
    0.78
    rack
    0.76
    roads
    0.75
    hemer
    0.74
     leap
    0.73
    opian
    0.73
    Act Density 0.035%

    No Known Activations