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

    Neuronpedia

    INDEX
    Explanations

    words related to beginnings or starting points

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to the beginning or start of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anamo
    -0.70
     Alloy
    -0.65
    ellow
    -0.63
    avorite
    -0.62
     Stories
    -0.61
    uni
    -0.61
     Fellow
    -0.60
    Anne
    -0.60
    ategor
    -0.59
    aylor
    -0.59
    POSITIVE LOGITS
    owment
    0.83
     thereof
    0.75
     loader
    0.69
    mentioned
    0.69
    currency
    0.65
     hust
    0.65
    formation
    0.64
     buds
    0.64
    quart
    0.61
    nels
    0.61
    Act Density 0.102%

    No Known Activations