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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate time duration or history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onse
    -0.18
    æ¦
    -0.16
    ë§ŀ
    -0.15
    usters
    -0.14
     voks
    -0.14
    еÑĢÑĤа
    -0.14
    antium
    -0.14
    aments
    -0.14
    aura
    -0.13
    kening
    -0.13
    POSITIVE LOGITS
    nat
    0.17
     Dial
    0.16
     Annunci
    0.15
     course
    0.15
    eken
    0.15
    abra
    0.14
    rench
    0.14
    Spacer
    0.14
    ires
    0.14
     distance
    0.14
    Act Density 0.033%

    No Known Activations