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

    Neuronpedia

    INDEX
    Explanations

    specific time-related terms or durations within narratives

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Later
    -0.88
     LATER
    -0.84
     Later
    -0.79
    later
    -0.78
     later
    -0.75
     subsequently
    -0.70
     Subsequent
    -0.70
    sequent
    -0.68
     Posteriormente
    -0.68
    StoryboardSegue
    -0.67
    POSITIVE LOGITS
     незавершена
    0.71
    awtextra
    0.64
    berdayakan
    0.57
    enderung
    0.56
     pulumi
    0.55
     unknownFields
    0.54
    :✨
    0.52
     considérons
    0.52
    laceae
    0.52
     gynhyrchwyd
    0.52
    Act Density 0.068%

    No Known Activations