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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time or sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to temporal phrases indicating actions or events occurring after a specific point in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aez
    -0.78
     constitu
    -0.68
    ements
    -0.67
    otaur
    -0.66
    ASE
    -0.65
    âĸĪâĸĪâĸĪâĸĪ
    -0.65
    Mask
    -0.65
    cci
    -0.63
    esian
    -0.63
    orio
    -0.63
    POSITIVE LOGITS
    noon
    1.14
    market
    0.99
    wards
    0.88
    thought
    0.86
     completing
    0.83
     takeoff
    0.82
     finishing
    0.81
     supper
    0.80
    words
    0.80
     awhile
    0.79
    Act Density 0.102%

    No Known Activations