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

    Neuronpedia

    INDEX
    Explanations

    elements related to variant or unique characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WI
    -0.15
    firm
    -0.14
    è³¢
    -0.13
     ëĶ
    -0.13
     firm
    -0.13
    ény
    -0.13
    regor
    -0.13
    astery
    -0.13
    elay
    -0.13
    atal
    -0.13
    POSITIVE LOGITS
     erb
    0.20
     allev
    0.20
     inset
    0.19
     muschi
    0.18
    .lin
    0.17
     ib
    0.16
     Angiosper
    0.16
     mamm
    0.16
     habitat
    0.16
     adulte
    0.16
    Act Density 0.008%

    No Known Activations