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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time references, particularly those related to events occurring before a specific moment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Macro
    -0.15
    zie
    -0.15
     fet
    -0.14
     Prel
    -0.14
    lescope
    -0.14
     course
    -0.13
    ues
    -0.13
     Kal
    -0.13
    eger
    -0.13
    flo
    -0.13
    POSITIVE LOGITS
     deadline
    0.16
    Zero
    0.16
    ilibrium
    0.15
    .recycle
    0.15
    olle
    0.15
    sgiving
    0.14
    nero
    0.14
    ikel
    0.14
    ono
    0.14
    illo
    0.14
    Act Density 0.130%

    No Known Activations