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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight uniqueness and innovation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antz
    -0.15
    isas
    -0.14
    orges
    -0.14
    enzhen
    -0.13
    308
    -0.13
    clas
    -0.13
    ayscale
    -0.13
    thood
    -0.13
    ancel
    -0.13
    iteli
    -0.13
    POSITIVE LOGITS
     unique
    0.26
     UNIQUE
    0.24
     Unique
    0.22
    Unique
    0.22
    unique
    0.21
    (unique
    0.19
     uniquely
    0.19
     uniqueness
    0.19
     unusual
    0.16
     uniq
    0.16
    Act Density 0.145%

    No Known Activations