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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the aims or objectives of studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppler
    -0.61
     frappé
    -0.59
     minOccurs
    -0.58
     underrated
    -0.53
     Drey
    -0.50
    omości
    -0.48
    chol
    -0.48
     linger
    -0.48
    weg
    -0.48
    (++
    -0.48
    POSITIVE LOGITS
     goal
    1.71
     aim
    1.71
     aims
    1.61
     objectives
    1.56
     goals
    1.56
     Goals
    1.46
     purpose
    1.45
     Goal
    1.45
    goal
    1.44
     tujuan
    1.42
    Act Density 0.189%

    No Known Activations