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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential actions or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    1
    -0.17
     finished
    -0.16
    essel
    -0.16
    eren
    -0.15
    ryn
    -0.15
    olog
    -0.15
    pio
    -0.15
    558
    -0.15
    pt
    -0.14
    pin
    -0.14
    POSITIVE LOGITS
    onnement
    0.15
    stery
    0.15
    quier
    0.15
    'gc
    0.15
    apgolly
    0.14
    gle
    0.14
    anka
    0.14
    ÃŃl
    0.14
    estro
    0.14
    ousel
    0.14
    Act Density 0.063%

    No Known Activations