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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation in expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    digital
    -0.14
    .lu
    -0.14
    aye
    -0.14
    quip
    -0.14
    diet
    -0.14
    å±ŀäºİ
    -0.14
    itle
    -0.13
    elez
    -0.13
    ../../
    -0.13
    amil
    -0.13
    POSITIVE LOGITS
    sb
    0.18
    nob
    0.17
    uba
    0.14
    ़
    0.14
    vert
    0.14
    verity
    0.14
     overnight
    0.14
    limits
    0.14
     regul
    0.14
    ssl
    0.14
    Act Density 0.131%

    No Known Activations