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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions of control or influence

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with indulgence and actions that suggest excess or intense behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceae
    -0.62
    Downloadha
    -0.55
     Werner
    -0.55
     reserved
    -0.55
     Scand
    -0.54
     nod
    -0.52
    Definition
    -0.52
     Ideal
    -0.51
     didnt
    -0.50
     objected
    -0.50
    POSITIVE LOGITS
    ulating
    1.53
    angering
    1.50
    ating
    1.50
    uting
    1.47
    ping
    1.45
    ouncing
    1.44
    ing
    1.44
    iting
    1.44
    iating
    1.43
    uing
    1.42
    Act Density 0.358%

    No Known Activations