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

    Neuronpedia

    INDEX
    Explanations

    phrases related to irreversibility or permanence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of irrelevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.77
    ramid
    -0.76
     guiActiveUnfocused
    -0.74
    ucket
    -0.72
     Trials
    -0.71
     Butterfly
    -0.71
     Hunters
    -0.70
    owler
    -0.69
     buckle
    -0.66
    DragonMagazine
    -0.64
    POSITIVE LOGITS
    voc
    1.26
    parable
    1.12
    lev
    0.93
     irre
    0.91
    agan
    0.91
    viation
    0.89
    asonable
    0.88
    cover
    0.87
    itable
    0.86
    putable
    0.85
    Act Density 0.018%

    No Known Activations