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

    Neuronpedia

    INDEX
    Explanations

    verbs related to giving and providing

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to providing or yielding something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansas
    -0.62
    ute
    -0.59
    verend
    -0.56
    ategy
    -0.55
    ä¸ī
    -0.55
    Originally
    -0.55
    ban
    -0.54
    cler
    -0.53
    arella
    -0.52
     Hungry
    -0.52
    POSITIVE LOGITS
     rise
    1.27
     us
    1.05
     birth
    0.95
    AW
    0.86
     cred
    0.82
     insight
    0.82
     ample
    0.80
     them
    0.80
     impetus
    0.79
    aways
    0.79
    Act Density 0.063%

    No Known Activations