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

    Neuronpedia

    INDEX
    Explanations

    verbs referring to a person's status or action, such as being, knowing, or managing

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    urry
    -0.77
    results
    -0.69
    urches
    -0.68
    ools
    -0.68
    ipers
    -0.66
     Ends
    -0.66
    uum
    -0.65
     peaks
    -0.65
    fail
    -0.64
    itized
    -0.64
    POSITIVE LOGITS
     currently
    1.17
     credited
    1.13
     married
    0.99
     adamant
    0.99
     proud
    0.99
     presently
    0.97
     flanked
    0.97
     obsessed
    0.96
     also
    0.95
     suing
    0.95
    Act Density 0.240%

    No Known Activations