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

    Neuronpedia

    INDEX
    Explanations

    sequences and durations of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    end dates or durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grotte
    -0.32
     cuchara
    -0.32
     cáps
    -0.32
    னை
    -0.30
     obrazu
    -0.30
     linho
    -0.29
     jaula
    -0.28
     lámpara
    -0.27
    tvguidetime
    -0.27
    orescent
    -0.27
    POSITIVE LOGITS
     until
    0.90
     <<<<<<<<<<<<<<
    0.89
     till
    0.88
    until
    0.84
    till
    0.71
    DockStyle
    0.71
     UNTIL
    0.71
     untill
    0.70
     Until
    0.70
    borderFill
    0.68
    Act Density 0.171%

    No Known Activations