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

    Neuronpedia

    INDEX
    Explanations

    references to concise summaries or accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceans
    -0.69
     Polo
    -0.64
    rogens
    -0.63
    onz
    -0.61
    ALD
    -0.59
     proced
    -0.57
    âĹ¼
    -0.57
    ILLE
    -0.57
    uben
    -0.56
    obal
    -0.56
    POSITIVE LOGITS
    cases
    1.39
    case
    1.38
    er
    0.89
    itud
    0.86
    erate
    0.78
    itude
    0.77
     stint
    0.75
     glimps
    0.74
    ings
    0.74
     periods
    0.73
    Act Density 0.049%

    No Known Activations