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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    overrides
    -0.15
    idot
    -0.14
    omanip
    -0.13
    /from
    -0.13
    izo
    -0.13
    stood
    -0.13
    iaux
    -0.13
    enga
    -0.13
    erton
    -0.13
    snapshot
    -0.13
    POSITIVE LOGITS
     order
    0.78
    order
    0.60
    -order
    0.51
     hopes
    0.49
     Order
    0.45
     ORDER
    0.43
     hope
    0.43
    .order
    0.42
    Order
    0.41
    _order
    0.41
    Act Density 0.301%

    No Known Activations