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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĿĽ
    -0.15
    strup
    -0.15
    rlen
    -0.14
    insky
    -0.14
    apper
    -0.14
    onta
    -0.14
    yx
    -0.14
    ÙĪع
    -0.14
    icontrol
    -0.14
     ########.
    -0.14
    POSITIVE LOGITS
     prisoners
    0.16
    else
    0.15
    лÑıд
    0.15
    enie
    0.15
    ul
    0.15
    owitz
    0.15
    алÑİ
    0.15
    u
    0.14
    stellung
    0.14
    uhl
    0.14
    Act Density 0.000%

    No Known Activations