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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a specific starting point or origin

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of "first," particularly in reference to precedence or priority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.66
    appiness
    -0.65
    bos
    -0.63
    Tags
    -0.61
    ourge
    -0.60
    pherd
    -0.59
    apego
    -0.58
    avior
    -0.55
    Insp
    -0.55
     Contributions
    -0.54
    POSITIVE LOGITS
     inning
    0.90
    imester
    0.87
     guise
    0.87
     installment
    0.81
     millennium
    0.79
     vicinity
    0.79
     stages
    0.79
     hurry
    0.78
     millenn
    0.77
     quarter
    0.76
    Act Density 0.093%

    No Known Activations