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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal matters or formal procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to "International" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILA
    -0.89
    éĹĺ
    -0.85
    artifacts
    -0.84
    姫
    -0.82
     Gleaming
    -0.80
    76561
    -0.78
    jriwal
    -0.77
    OHN
    -0.77
    士
    -0.77
    çĦ
    -0.76
    POSITIVE LOGITS
    ellect
    1.13
    ention
    1.08
    ensity
    1.01
    uitive
    1.01
    estinal
    1.00
    angible
    0.97
    ensive
    0.93
    ellig
    0.85
    ensions
    0.81
    ensible
    0.81
    Act Density 0.005%

    No Known Activations