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

    Neuronpedia

    INDEX
    Explanations

    strong matches with words related to factual information

    oai_token-act-pair · gpt-3.5-turbo

    references to factual information and its importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osi
    -0.90
    interstitial
    -0.82
    ebus
    -0.79
    irts
    -0.79
    yss
    -0.79
    isoft
    -0.77
    ovo
    -0.73
    rint
    -0.72
    athetic
    -0.72
    hod
    -0.71
    POSITIVE LOGITS
    fulness
    0.94
    heet
    0.92
     facts
    0.82
    telling
    0.82
     inacc
    0.81
    facts
    0.81
     surrounding
    0.76
    sheet
    0.75
    sheets
    0.73
     pertaining
    0.72
    Act Density 0.021%

    No Known Activations