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

    Neuronpedia

    INDEX
    Explanations

    phrases describing products or services and their attributes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating accompanying features or benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.71
    jab
    -0.69
    chan
    -0.69
     Archdemon
    -0.63
    pmwiki
    -0.63
     Trance
    -0.61
    Attempts
    -0.60
    axis
    -0.60
    marg
    -0.58
    antis
    -0.58
    POSITIVE LOGITS
     regards
    0.94
     regard
    0.92
    stood
    0.91
    drawn
    0.83
     luggage
    0.75
     groceries
    0.75
     respect
    0.74
     plenty
    0.74
     loads
    0.72
     dignity
    0.71
    Act Density 0.051%

    No Known Activations