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

    Neuronpedia

    INDEX
    Explanations

    phrases related to introducing or discussing a topic or person

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¡
    -0.72
    Own
    -0.67
    angan
    -0.65
    ochond
    -0.64
    Minecraft
    -0.64
    aretz
    -0.64
    fal
    -0.63
    current
    -0.63
    quest
    -0.62
    ias
    -0.61
    POSITIVE LOGITS
     same
    0.90
    same
    0.78
     Author
    0.74
     size
    0.73
     dozen
    0.71
     halfway
    0.69
    tin
    0.68
     bend
    0.65
     Authors
    0.65
     holidays
    0.61
    Act Density 0.081%

    No Known Activations