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

    Neuronpedia

    INDEX
    Explanations

    phrases related to seeing or witnessing events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to observations and trends in societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.72
     sugg
    -0.71
     Dietary
    -0.67
     Brah
    -0.66
     STE
    -0.64
     Wond
    -0.61
     Recomm
    -0.61
     Fas
    -0.60
     Fahrenheit
    -0.58
     DX
    -0.58
    POSITIVE LOGITS
     unfold
    0.94
    aily
    0.76
    progress
    0.69
     emerge
    0.68
    amorph
    0.67
     fade
    0.66
     firsthand
    0.66
    aeus
    0.66
     evolve
    0.65
    grow
    0.65
    Act Density 0.421%

    No Known Activations