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

    Neuronpedia

    INDEX
    Explanations

    instances where the text refers to qualification, registration, or grouping of people or things

    oai_token-act-pair · gpt-3.5-turbo

    terms related to registration and qualifying processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rought
    -0.59
    hire
    -0.57
    geoning
    -0.56
    thing
    -0.56
    ija
    -0.56
     aggregation
    -0.55
    VA
    -0.55
    ĸļ
    -0.54
    issue
    -0.54
    hoe
    -0.54
    POSITIVE LOGITS
     peacefully
    1.03
     themselves
    0.93
     oneself
    0.87
     accordingly
    0.86
     seamlessly
    0.80
     spontaneously
    0.79
     herself
    0.77
     comfortably
    0.77
     himself
    0.76
     prematurely
    0.75
    Act Density 0.306%

    No Known Activations