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

    Neuronpedia

    INDEX
    Explanations

    descriptions of hairstyles and hair characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pell
    -0.15
    é¼»
    -0.14
     Ñģи
    -0.14
    ivot
    -0.14
    çĵ
    -0.14
     Lens
    -0.13
    lam
    -0.13
     Wort
    -0.13
     label
    -0.13
     yurt
    -0.13
    POSITIVE LOGITS
     bun
    0.32
     bra
    0.31
     pony
    0.30
     Bun
    0.27
     Pony
    0.24
     pinned
    0.24
     Bra
    0.23
    pon
    0.23
     undone
    0.22
    bra
    0.21
    Act Density 0.029%

    No Known Activations