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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "learned"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "learned."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abwe
    -0.77
    idity
    -0.68
    oided
    -0.65
    ataka
    -0.64
    rake
    -0.62
    heads
    -0.62
    abases
    -0.61
    viks
    -0.61
    idia
    -0.60
    vati
    -0.60
    POSITIVE LOGITS
     firsthand
    0.89
    llor
    0.82
    ilage
    0.77
     Curve
    0.75
     Learned
    0.75
    æĥ
    0.75
     srfAttach
    0.74
    Lear
    0.74
    çīĪ
    0.74
     Lauder
    0.72
    Act Density 0.028%

    No Known Activations