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

    Neuronpedia

    INDEX
    Explanations

    phrases related to foundational elements

    oai_token-act-pair · gpt-3.5-turbo

    the word "which" and its context in various phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aiden
    -0.76
    swick
    -0.71
    DIT
    -0.70
     WATCHED
    -0.67
    marg
    -0.66
     ACPI
    -0.65
     Panda
    -0.65
    Charg
    -0.62
    unts
    -0.61
    fml
    -0.61
    POSITIVE LOGITS
    soever
    0.99
    izens
    0.77
    sein
    0.69
     judgments
    0.65
     they
    0.64
    xual
    0.63
    ordan
    0.62
     we
    0.61
    awaru
    0.61
    isson
    0.61
    Act Density 0.031%

    No Known Activations