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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a time frame or future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zp
    -0.15
    acht
    -0.15
    anchise
    -0.14
    034
    -0.14
    611
    -0.14
     Gors
    -0.14
    zych
    -0.14
    onet
    -0.14
    agas
    -0.14
    UGH
    -0.13
    POSITIVE LOGITS
    asty
    0.14
    Ĥ¬
    0.14
    sto
    0.14
    ÏĦοκ
    0.14
     глÑĥ
    0.14
    ιαν
    0.14
    ±
    0.14
    cession
    0.14
    eo
    0.14
    .namespace
    0.13
    Act Density 0.011%

    No Known Activations