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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions or durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a passage of time since the last occurrence of an event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Jewish
    -0.72
    Bird
    -0.70
    flo
    -0.65
    Christian
    -0.65
     Masonic
    -0.64
    BUT
    -0.64
    Catholic
    -0.63
    Fal
    -0.62
    Secondly
    -0.62
    gravity
    -0.61
    POSITIVE LOGITS
    rely
    0.83
     inception
    0.70
     CrossRef
    0.70
    oresc
    0.70
     defeat
    0.69
     enactment
    0.68
     elapsed
    0.67
     landfall
    0.66
     kickoff
    0.66
     acclaimed
    0.65
    Act Density 0.040%

    No Known Activations