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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or goals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "take" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accompanies
    -0.74
     agre
    -0.70
    tions
    -0.67
    ese
    -0.67
    hess
    -0.63
    ateg
    -0.60
    Gear
    -0.60
    rehens
    -0.58
    ominated
    -0.58
    vine
    -0.58
    POSITIVE LOGITS
     advantage
    1.42
     care
    1.02
    aways
    1.02
     aback
    0.94
     liberties
    0.94
     away
    0.93
    advant
    0.90
     cues
    0.88
     pains
    0.88
     responsibility
    0.87
    Act Density 0.092%

    No Known Activations