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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to confidentiality and the protection of sensitive information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imes
    -0.17
    úa
    -0.16
    ovit
    -0.15
    spender
    -0.15
    ichten
    -0.15
    strup
    -0.15
    strand
    -0.14
    arde
    -0.14
    fone
    -0.14
    onta
    -0.14
    POSITIVE LOGITS
    omit
    0.18
    ãĥ«ãĤ¯
    0.17
    /conf
    0.16
    ness
    0.14
    itor
    0.14
    ays
    0.14
    osy
    0.14
    ossip
    0.13
    nce
    0.13
    ople
    0.13
    Act Density 0.026%

    No Known Activations