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

    Neuronpedia

    INDEX
    Explanations

    action verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or states, particularly using the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    comings
    -0.64
     Reasons
    -0.62
     Spartans
    -0.62
    eworld
    -0.61
     rivals
    -0.61
     results
    -0.60
     nearer
    -0.59
     TIM
    -0.59
    arching
    -0.59
    tones
    -0.59
    POSITIVE LOGITS
     nominate
    0.94
     emulate
    0.88
     reproduce
    0.88
     create
    0.88
    create
    0.87
    apply
    0.86
     remove
    0.85
     rename
    0.85
     organize
    0.84
     innovate
    0.84
    Act Density 0.169%

    No Known Activations