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

    Neuronpedia

    INDEX
    Explanations

    concepts related to separation and isolation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ery
    -0.19
    ry
    -0.16
    erm
    -0.16
    elen
    -0.15
    compass
    -0.15
    estate
    -0.15
    egin
    -0.15
    pone
    -0.15
    ulin
    -0.15
    ermen
    -0.15
    POSITIVE LOGITS
    /div
    0.21
    -sex
    0.18
    /group
    0.17
    ĶåĽŀ
    0.17
    yor
    0.16
     khá»ıi
    0.16
     sexes
    0.16
    inç
    0.16
    گاÙĨ
    0.16
    mint
    0.16
    Act Density 0.030%

    No Known Activations