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

    Neuronpedia

    INDEX
    Explanations

    phrases containing positive evaluations and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to food and recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ictions
    -0.73
     assurances
    -0.72
    lings
    -0.68
    facts
    -0.68
    rones
    -0.67
     speeches
    -0.67
    itement
    -0.67
     quotas
    -0.64
    uckles
    -0.64
     Lack
    -0.63
    POSITIVE LOGITS
     versatile
    1.19
     useful
    1.01
     underrated
    1.01
     unbeat
    0.99
     aest
    0.99
     excellent
    0.97
     playable
    0.96
     suitable
    0.93
     ideal
    0.91
     perfect
    0.90
    Act Density 0.542%

    No Known Activations