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

    Neuronpedia

    INDEX
    Explanations

    concepts related to silence and inactivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intStringLen
    -0.36
     teacher
    -0.36
     risque
    -0.36
    ientôt
    -0.35
     owns
    -0.35
    └──
    -0.35
    FINISH
    -0.34
    contentValues
    -0.34
     concom
    -0.34
    󠁢
    -0.34
    POSITIVE LOGITS
     silence
    0.63
     inaction
    0.59
    ंदीखरीदारी
    0.57
    silence
    0.57
     ignore
    0.56
     ignored
    0.55
     silêncio
    0.54
    HideFlags
    0.53
     silencio
    0.52
    Silence
    0.51
    Act Density 1.067%

    No Known Activations