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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating preference or substitution

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating preference or choices in favor of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estate
    -0.75
    iana
    -0.69
    caster
    -0.68
    "]=>
    -0.67
    Initialized
    -0.67
    >[
    -0.66
    affected
    -0.65
    problem
    -0.63
    iott
    -0.63
     proble
    -0.63
    POSITIVE LOGITS
    livion
    0.79
     manageable
    0.71
     rubble
    0.69
    azel
    0.67
     nearest
    0.64
     piles
    0.63
     pasture
    0.62
     plain
    0.61
     paste
    0.60
    Tier
    0.59
    Act Density 0.566%

    No Known Activations