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

    Neuronpedia

    INDEX
    Explanations

    expressions related to excitement or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TED
    -0.15
     nug
    -0.15
    ãĥ©ãĤ¤ãĥ³
    -0.14
    ilst
    -0.14
    rieb
    -0.13
    usted
    -0.13
    ë¥ĺ
    -0.13
    ç§ģãģ¯
    -0.13
    anlık
    -0.13
     HÃł
    -0.13
    POSITIVE LOGITS
    sha
    0.15
     Surround
    0.15
    .AC
    0.15
     Shel
    0.15
    cha
    0.15
     Birch
    0.14
     ensemble
    0.14
    handles
    0.14
    inde
    0.14
     blinds
    0.14
    Act Density 0.140%

    No Known Activations