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

    Neuronpedia

    INDEX
    Explanations

    instances of comparison phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .apps
    -0.16
    istr
    -0.15
    ik
    -0.15
    ç·Ĵ
    -0.14
     ATTRIBUTE
    -0.14
    anks
    -0.14
    нок
    -0.14
    LS
    -0.14
    PP
    -0.14
    readcr
    -0.14
    POSITIVE LOGITS
    aeda
    0.18
    eker
    0.17
    unto
    0.16
    adero
    0.15
     INA
    0.14
    wert
    0.14
    eshire
    0.14
    åIJ«
    0.14
    rente
    0.14
    ickets
    0.14
    Act Density 0.015%

    No Known Activations