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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progression or actions taken over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zes
    -0.16
    ãĤ§
    -0.16
    leston
    -0.15
    è©
    -0.15
    ufe
    -0.14
    ching
    -0.14
    ÑĪкÑĥ
    -0.14
    ynn
    -0.14
    »
    -0.14
    .lu
    -0.13
    POSITIVE LOGITS
    iot
    0.17
    ioc
    0.15
    pline
    0.15
    iT
    0.15
    853
    0.14
    884
    0.14
    mî
    0.14
    erb
    0.14
    ubar
    0.14
    QN
    0.14
    Act Density 0.018%

    No Known Activations