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

    Neuronpedia

    INDEX
    Explanations

    phrases that address or refer to the reader directly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æŁ
    -0.16
     Uns
    -0.15
    VIC
    -0.15
    blick
    -0.15
    ufe
    -0.15
    ocr
    -0.15
    viso
    -0.14
    HOOK
    -0.14
    /post
    -0.14
     Trident
    -0.14
    POSITIVE LOGITS
    æ¨Ĥ
    0.15
    iz
    0.15
     forg
    0.14
     des
    0.14
    Ī¬
    0.14
     cann
    0.13
     nÄĥ
    0.13
    isc
    0.13
    át
    0.13
     conn
    0.13
    Act Density 0.005%

    No Known Activations