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

    Neuronpedia

    INDEX
    Explanations

    phrases and words associated with questioning or seeking explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zot
    -0.15
     ÙĪاÙĦÙĨ
    -0.15
    éĬ
    -0.14
     Nate
    -0.14
    TZ
    -0.14
    ilet
    -0.14
    ween
    -0.14
    amber
    -0.13
    hil
    -0.13
     Calc
    -0.13
    POSITIVE LOGITS
     Vog
    0.15
     sens
    0.14
     Kral
    0.14
    ascript
    0.14
    436
    0.14
     aggressive
    0.13
    phet
    0.13
    говоÑĢ
    0.13
    926
    0.13
    erset
    0.13
    Act Density 0.004%

    No Known Activations