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

    Neuronpedia

    INDEX
    Explanations

    situations where a person will feel a specific emotion or experience a particular outcome

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to expectations or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osate
    -0.66
     corpus
    -0.64
     mandate
    -0.63
     relativity
    -0.63
     constellation
    -0.62
     guise
    -0.62
     distinction
    -0.62
     Genius
    -0.62
     suggestion
    -0.61
     Stability
    -0.61
    POSITIVE LOGITS
     able
    1.32
     glad
    1.04
     amazed
    1.01
     thankful
    1.00
     rewarded
    0.99
     surprised
    0.98
     tempted
    0.95
     grateful
    0.94
     forgiven
    0.91
    heading
    0.89
    Act Density 0.141%

    No Known Activations