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

    Neuronpedia

    INDEX
    Explanations

    phrases describing activities or events happening at a specific time or location

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experiences and urgent situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     predec
    -0.67
     grouping
    -0.62
     memorable
    -0.61
    Ö¼
    -0.60
     awarding
    -0.59
     thereof
    -0.58
     Cham
    -0.58
     ranking
    -0.58
    vg
    -0.57
     Naj
    -0.56
    POSITIVE LOGITS
    edge
    0.77
    cakes
    0.76
     lately
    0.74
    acid
    0.73
    FIELD
    0.69
    border
    0.68
    ey
    0.67
    cake
    0.66
    olin
    0.65
    bern
    0.64
    Act Density 0.881%

    No Known Activations