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

    Neuronpedia

    INDEX
    Explanations

    words related to the beginning or starting of events or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the initiation or commencement of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighth
    -0.66
    aths
    -0.64
    izontal
    -0.63
     Britann
    -0.60
    é¾įå
    -0.60
    è£ħ
    -0.59
    aiden
    -0.58
     Utilities
    -0.58
    ordinate
    -0.57
    pload
    -0.57
    POSITIVE LOGITS
     creeping
    0.89
     unravel
    0.88
     anew
    0.85
     behaving
    0.85
     disappearing
    0.82
     crumbling
    0.79
     leaking
    0.78
     trending
    0.77
     popping
    0.77
     piling
    0.76
    Act Density 0.088%

    No Known Activations