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

    Neuronpedia

    INDEX
    Explanations

    references to television and other media formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    E
    -0.25
    ECTOR
    -0.23
    T
    -0.20
    TION
    -0.19
    TURE
    -0.18
    TXT
    -0.18
    EAR
    -0.18
    aires
    -0.17
    ARRANT
    -0.17
    Sdk
    -0.17
    POSITIVE LOGITS
    s
    0.37
    /OR
    0.29
    aaS
    0.26
    sWith
    0.22
    ’S
    0.22
    sian
    0.19
    sak
    0.19
    'er
    0.19
    sik
    0.19
    sut
    0.19
    Act Density 0.898%

    No Known Activations