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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "during" and other temporal markers related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cheated
    -0.13
    ual
    -0.13
    ometer
    -0.12
    ê·¹
    -0.12
    aye
    -0.12
     велиÑĩ
    -0.12
    ories
    -0.12
    สาร
    -0.12
     bells
    -0.12
    liga
    -0.12
    POSITIVE LOGITS
     periods
    0.32
     times
    0.29
     the
    0.27
     this
    0.26
     their
    0.25
     infancy
    0.24
     peak
    0.24
     its
    0.24
     these
    0.23
     breaks
    0.23
    Act Density 0.060%

    No Known Activations