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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of widows

    oai_token-act-pair · gpt-3.5-turbo

    terms related to widows and orphans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.66
    ebook
    -0.64
     guid
    -0.62
    asper
    -0.62
    Inst
    -0.60
     Mane
    -0.60
     Breach
    -0.60
    inez
    -0.60
    Ú
    -0.60
    Temp
    -0.59
    POSITIVE LOGITS
     widow
    1.19
    hood
    1.00
    iciary
    0.98
    bush
    0.96
    nesday
    0.88
    doms
    0.88
     wid
    0.84
    rift
    0.81
    sylv
    0.79
    creen
    0.78
    Act Density 0.031%

    No Known Activations