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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reactions and responses in a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    responses characterized by strong emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Inher
    -0.72
    ritten
    -0.70
     ceilings
    -0.65
     inherited
    -0.61
    tenance
    -0.60
     Reincarnated
    -0.59
    properties
    -0.59
    Limit
    -0.58
     prized
    -0.58
     ledger
    -0.58
    POSITIVE LOGITS
     incred
    0.79
     disbelief
    0.76
     affirmative
    0.75
     fury
    0.72
     hostility
    0.72
     kindness
    0.71
     Cancel
    0.70
     response
    0.70
     denial
    0.68
    rique
    0.68
    Act Density 0.152%

    No Known Activations