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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and expressions, including inequalities and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥį
    -0.18
    erson
    -0.16
    thal
    -0.16
    "';
    -0.15
    @email
    -0.15
    anian
    -0.15
    qed
    -0.14
    oldem
    -0.14
    "<?
    -0.14
    ERAL
    -0.14
    POSITIVE LOGITS
    istrovstvÃŃ
    0.17
    à¹ij
    0.17
    ertz
    0.14
    íĨłíĨł
    0.14
    oltip
    0.14
    *)&
    0.13
    woord
    0.13
     Barr
    0.13
    harma
    0.13
    iy
    0.13
    Act Density 0.102%

    No Known Activations