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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate a specific intention or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to intentions or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Solitaire
    -0.79
    PASS
    -0.75
     Skies
    -0.71
     Towns
    -0.70
    UX
    -0.69
    Mini
    -0.68
    Score
    -0.66
     knots
    -0.66
    --------------------------------------------------------
    -0.65
    Versions
    -0.65
    POSITIVE LOGITS
    lessly
    1.17
    amental
    0.95
    gha
    0.90
    emouth
    0.87
    atory
    0.87
    lessness
    0.85
    ality
    0.83
    alogue
    0.82
    eers
    0.80
     aim
    0.79
    Act Density 0.005%

    No Known Activations