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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being part of a larger initiative or action

    oai_token-act-pair · gpt-3.5-turbo

    references to being part of something larger or collective actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unbeliev
    -0.61
     unheard
    -0.58
     millenn
    -0.58
     notor
    -0.57
     destro
    -0.57
     defic
    -0.56
     cumbers
    -0.56
     satell
    -0.56
     tyr
    -0.54
     heights
    -0.54
    POSITIVE LOGITS
    ridge
    0.91
     of
    0.87
    aking
    0.82
    ridges
    0.76
    meal
    0.74
     thereof
    0.74
    displayText
    0.73
    ration
    0.69
    onement
    0.69
    icles
    0.66
    Act Density 0.024%

    No Known Activations