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

    Neuronpedia

    INDEX
    Explanations

    unique or unparalleled experiences or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èµ·
    -0.15
    ando
    -0.15
    onse
    -0.14
    extras
    -0.14
    éĥ½å¸Ĥ
    -0.13
    ãĥĬãĥ«
    -0.13
    cust
    -0.13
     Actual
    -0.13
    ãĥ¼ãĥī
    -0.13
     éĸ
    -0.13
    POSITIVE LOGITS
     unique
    0.36
    unique
    0.34
     uniqueness
    0.33
     Unique
    0.32
    Unique
    0.32
     UNIQUE
    0.30
    (unique
    0.26
     uniq
    0.26
    _unique
    0.24
    .Unique
    0.22
    Act Density 0.157%

    No Known Activations