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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases such as lengths of time and hours worked

    oai_token-act-pair · gpt-3.5-turbo

    references to units of time and age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifice
    -0.74
    icably
    -0.72
    INST
    -0.66
    culus
    -0.65
    untled
    -0.64
    emis
    -0.64
    ashtra
    -0.63
    thy
    -0.63
    ingu
    -0.63
    hin
    -0.63
    POSITIVE LOGITS
     olds
    1.27
     increments
    1.23
     intervals
    1.11
    frames
    1.01
     equivalents
    0.90
     periods
    0.90
     cycles
    0.85
     lengths
    0.85
    rees
    0.82
     spans
    0.81
    Act Density 0.082%

    No Known Activations