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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating upward movement or escalation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leich
    -0.15
    éry
    -0.15
    t
    -0.15
    .cleanup
    -0.15
    Vectorizer
    -0.14
    دÙĪ
    -0.14
    away
    -0.14
    elen
    -0.14
    νομ
    -0.14
    ecal
    -0.14
    POSITIVE LOGITS
    bben
    0.15
    upa
    0.15
    bris
    0.15
     beden
    0.14
    æŁ±
    0.14
     pillar
    0.14
     rè
    0.14
    !=(
    0.14
    ä¹ĺ
    0.14
     slack
    0.13
    Act Density 0.044%

    No Known Activations