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

    Neuronpedia

    INDEX
    Explanations

    passages involving a transformation or change in identity or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strous
    -0.64
    pedia
    -0.61
    rador
    -0.61
     Explosion
    -0.60
     stakes
    -0.59
     Bars
    -0.58
     todd
    -0.58
     Mund
    -0.58
     Police
    -0.58
     emerges
    -0.57
    POSITIVE LOGITS
     able
    1.07
    hemoth
    0.98
    ardless
    0.98
     judged
    0.95
    leeve
    0.94
    heading
    0.92
    ech
    0.90
    fits
    0.90
    league
    0.89
    ijing
    0.88
    Act Density 0.331%

    No Known Activations