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

    Neuronpedia

    INDEX
    Explanations

    statistics and numerical data related to usage, performance, or demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egin
    -0.17
    363
    -0.17
    RSS
    -0.15
    robat
    -0.15
    WARDED
    -0.14
    loff
    -0.14
    istrovstvÃŃ
    -0.14
    semb
    -0.14
    mong
    -0.14
    egative
    -0.14
    POSITIVE LOGITS
    cir
    0.28
     around
    0.28
     circa
    0.28
    around
    0.24
     broadly
    0.23
     Around
    0.23
    Around
    0.23
     anything
    0.21
     nearer
    0.20
     just
    0.20
    Act Density 0.170%

    No Known Activations