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

    Neuronpedia

    INDEX
    Explanations

    time-related durations or intervals

    oai_token-act-pair · gpt-3.5-turbo

    references to duration, particularly time intervals measured in minutes, hours, days, and weeks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rium
    -0.69
    Registered
    -0.69
    cheat
    -0.67
    egu
    -0.67
    erer
    -0.65
    ocl
    -0.65
    rose
    -0.63
    erers
    -0.63
    done
    -0.62
    gall
    -0.62
    POSITIVE LOGITS
     sake
    0.98
     purposes
    0.89
    iatus
    0.81
     consecut
    0.81
     duration
    0.78
     periods
    0.77
     apiece
    0.77
     uninterrupted
    0.77
    uda
    0.76
     reasons
    0.73
    Act Density 0.097%

    No Known Activations