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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actly
    -0.16
    ther
    -0.16
    ment
    -0.15
    ightly
    -0.15
    sky
    -0.15
    imbus
    -0.15
    ns
    -0.15
    amente
    -0.15
    icum
    -0.14
     Fus
    -0.14
    POSITIVE LOGITS
    oretical
    0.27
    oret
    0.18
    odore
    0.17
    orem
    0.16
    atre
    0.16
    orical
    0.16
    /Dk
    0.15
    ocracy
    0.15
    issen
    0.15
    otime
    0.15
    Act Density 0.294%

    No Known Activations