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

    Neuronpedia

    INDEX
    Explanations

    events or actions being initiated or commencing

    oai_token-act-pair · gpt-3.5-turbo

    instances of phrases indicating the beginning of events or stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LP
    -0.67
    arta
    -0.62
    lah
    -0.62
    aster
    -0.62
     congratulated
    -0.62
     Parables
    -0.61
     reused
    -0.59
    ethy
    -0.59
    grand
    -0.58
    otropic
    -0.57
    POSITIVE LOGITS
     innoc
    1.20
     anew
    0.90
     when
    0.89
     with
    0.89
     spontaneously
    0.86
     raining
    0.85
     shortly
    0.78
     peacefully
    0.78
     somewhere
    0.76
     abruptly
    0.75
    Act Density 0.062%

    No Known Activations