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

    Neuronpedia

    INDEX
    Explanations

    dates and temporal markers that indicate specific timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umb
    -0.15
     upstream
    -0.15
    llib
    -0.14
    _between
    -0.14
     sooner
    -0.14
    Äĵ
    -0.14
    ynet
    -0.13
    ioni
    -0.13
    Between
    -0.13
    vé
    -0.13
    POSITIVE LOGITS
     forward
    0.57
     onwards
    0.53
     onward
    0.50
    Forward
    0.49
     Forward
    0.49
    forward
    0.49
    _forward
    0.42
     FORWARD
    0.42
    -forward
    0.42
    .forward
    0.42
    Act Density 0.166%

    No Known Activations