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

    Neuronpedia

    INDEX
    Explanations

    phrases related to daily activities or routines

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time, specifically "day-to-day" references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reluct
    -0.71
    ©¶æ¥µ
    -0.66
    ailability
    -0.65
     adolesc
    -0.56
     cumbers
    -0.54
     undermin
    -0.54
     proport
    -0.54
    ŃĶ
    -0.54
    ĸļ
    -0.53
     unnecess
    -0.52
    POSITIVE LOGITS
    -
    0.94
    pping
    0.74
    -[
    0.71
    ilet
    0.70
    dden
    0.69
    -$
    0.69
    -,
    0.69
    _-_
    0.69
    '-
    0.65
    -(
    0.64
    Act Density 0.017%

    No Known Activations