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

    Neuronpedia

    INDEX
    Explanations

    references to relatable experiences or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igion
    -0.19
    een
    -0.18
    rap
    -0.17
    Ïİ
    -0.17
    ronym
    -0.17
    610
    -0.16
    acion
    -0.16
    rame
    -0.16
    ateurs
    -0.15
    efeller
    -0.15
    POSITIVE LOGITS
    atable
    0.25
    iefs
    0.23
    ished
    0.23
    ays
    0.23
    ishes
    0.22
    ieves
    0.21
    atab
    0.21
    ativity
    0.20
    aying
    0.20
    ishing
    0.20
    Act Density 0.004%

    No Known Activations