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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations commonly used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enti
    -0.17
    ough
    -0.15
     /
    -0.15
    ologically
    -0.14
    nett
    -0.14
    otts
    -0.14
    ابÛĮ
    -0.14
    äºĭ
    -0.13
     cracking
    -0.13
    --+
    -0.13
    POSITIVE LOGITS
    cite
    0.31
    cit
    0.21
     cite
    0.19
     cit
    0.19
    cre
    0.17
    pretty
    0.17
    pag
    0.16
    Uniform
    0.16
    Gate
    0.15
    eland
    0.15
    Act Density 0.032%

    No Known Activations