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

    Neuronpedia

    INDEX
    Explanations

    proper nouns starting with 'Gue'

    oai_token-act-pair · gpt-3.5-turbo

    the name "Guvara" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atform
    -0.66
     absorbing
    -0.61
    practice
    -0.61
    worms
    -0.60
    Agg
    -0.58
     continents
    -0.58
     mids
    -0.58
    arna
    -0.57
    romeda
    -0.57
    Frameworks
    -0.57
    POSITIVE LOGITS
    lla
    1.10
    llo
    0.97
    ue
    0.93
    pees
    0.92
    pee
    0.89
    lect
    0.84
    lly
    0.82
    lette
    0.82
    ño
    0.82
    hler
    0.81
    Act Density 0.010%

    No Known Activations