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

    Neuronpedia

    INDEX
    Explanations

    terms related to breaks or vacations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    periods of time off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.57
     myſelf
    -0.57
     baumwolle
    -0.57
    ſelf
    -0.56
     unſ
    -0.56
     ſind
    -0.55
     raiſ
    -0.55
     iſt
    -0.55
    KommentareTeilen
    -0.54
     UIColor
    -0.53
    POSITIVE LOGITS
     recess
    0.54
     vacation
    0.52
     vacations
    0.49
     WEEKEND
    0.48
     weekend
    0.48
    ferien
    0.48
     Break
    0.48
     break
    0.47
     intermission
    0.47
     Vacation
    0.45
    Act Density 0.006%

    No Known Activations