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

    Neuronpedia

    INDEX
    Explanations

    specific questions or statements

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases that introduce information or insights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    robe
    -0.77
    uttering
    -0.70
    gas
    -0.68
     favour
    -0.63
    Term
    -0.62
    Ħ¢
    -0.62
    ench
    -0.62
    aith
    -0.62
    cise
    -0.61
    ãĥ¼
    -0.61
    POSITIVE LOGITS
     happens
    1.00
     separates
    0.84
     happened
    0.82
     transpired
    0.76
    pedia
    0.75
     exactly
    0.73
     Wikipedia
    0.72
     happen
    0.71
     happ
    0.69
    arcity
    0.64
    Act Density 0.053%

    No Known Activations