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

    Neuronpedia

    INDEX
    Explanations

    temporal references and sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duga
    -0.45
    hynch
    -0.41
     voordat
    -0.41
    ting
    -0.41
    tées
    -0.41
     Producing
    -0.40
    idhi
    -0.40
    active
    -0.39
    หว่าง
    -0.39
    intios
    -0.38
    POSITIVE LOGITS
     onwards
    2.43
     onward
    2.15
     forward
    1.56
     upwards
    1.49
     upward
    1.35
    forward
    1.34
     adelante
    1.33
     downwards
    1.32
     forwards
    1.29
    Forward
    1.20
    Act Density 0.126%

    No Known Activations