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

    Neuronpedia

    INDEX
    Explanations

    transitions and conditionals in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     into
    -0.14
    imonial
    -0.14
    ston
    -0.13
    ija
    -0.13
    to
    -0.13
     to
    -0.13
     Ey
    -0.12
    intColor
    -0.12
    aye
    -0.12
    esson
    -0.12
    POSITIVE LOGITS
    ,
    0.16
    дап
    0.14
    soever
    0.13
    siyon
    0.13
    ,↵↵
    0.13
    –↵↵
    0.13
    .ga
    0.13
    Ậ
    0.12
    abras
    0.12
     tarif
    0.12
    Act Density 0.352%

    No Known Activations