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

    Neuronpedia

    INDEX
    Explanations

    words related to mysterious or supernatural concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to the supernatural, uncanny events, and critical social commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     warr
    -0.66
     obser
    -0.66
    Sov
    -0.65
     colleagues
    -0.61
    Ms
    -0.61
    ĪĴ
    -0.59
     linem
    -0.59
    words
    -0.58
    sbm
    -0.58
    pec
    -0.57
    POSITIVE LOGITS
    ritz
    0.92
    elight
    0.80
    liest
    0.77
    ospace
    0.71
    osphere
    0.68
     (%)
    0.66
    cients
    0.66
     underworld
    0.66
    vre
    0.65
    archy
    0.65
    Act Density 0.770%

    No Known Activations