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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific examples or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _exceptions
    -0.15
     Towers
    -0.15
    Pocket
    -0.15
    339
    -0.15
    ide
    -0.14
    /mock
    -0.14
    apture
    -0.14
    alace
    -0.13
    iesel
    -0.13
    cock
    -0.13
    POSITIVE LOGITS
     sake
    0.16
    utz
    0.15
    shal
    0.15
    ERM
    0.15
    sehen
    0.15
    ereg
    0.14
    ÑģиÑĤ
    0.14
    ãģĪãģ°
    0.14
     Abs
    0.14
     ÙħØ·
    0.13
    Act Density 0.025%

    No Known Activations