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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating accessibility and conditions of engagement or commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kings
    -0.17
    chner
    -0.15
    elerik
    -0.15
    akte
    -0.15
    íĶĪ
    -0.15
    imos
    -0.14
     same
    -0.14
    wap
    -0.14
    ets
    -0.14
    ype
    -0.14
    POSITIVE LOGITS
    razier
    0.16
    -val
    0.15
    onso
    0.15
    anj
    0.15
    onto
    0.15
    494
    0.15
    anne
    0.15
    ocha
    0.14
    oggler
    0.14
    owers
    0.14
    Act Density 0.012%

    No Known Activations