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

    Neuronpedia

    INDEX
    Explanations

    a variety of situations or options in discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    OIL
    -0.75
    nothing
    -0.74
    heed
    -0.73
    timer
    -0.72
    mol
    -0.71
    odon
    -0.67
    NP
    -0.66
     EVER
    -0.65
    Quote
    -0.65
    mit
    -0.65
    POSITIVE LOGITS
     kinds
    1.66
     types
    1.53
    iating
    1.50
     aspects
    1.36
     configurations
    1.34
     facets
    1.32
     combinations
    1.31
     styles
    1.30
     genres
    1.27
     disciplines
    1.25
    Act Density 1.764%

    No Known Activations