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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings or court activities

    oai_token-act-pair · gpt-3.5-turbo

    the end of the document or completion signals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.81
    smanship
    -0.66
    wright
    -0.65
    egu
    -0.64
    10000
    -0.64
     Seym
    -0.63
    å£
    -0.60
    aky
    -0.60
    zona
    -0.60
    athan
    -0.58
    POSITIVE LOGITS
    bidden
    0.90
     example
    0.84
     instance
    0.82
    gery
    0.77
    gotten
    0.75
     sale
    0.75
     awhile
    0.74
    geries
    0.71
    ked
    0.69
    WARD
    0.69
    Act Density 0.041%

    No Known Activations