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

    Neuronpedia

    INDEX
    Explanations

    words related to declaring statements or judgments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to formal declarations or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.78
     Hole
    -0.77
    âĶģ
    -0.69
    culosis
    -0.68
     priv
    -0.66
    ĸļ
    -0.66
    nesday
    -0.65
     GOODMAN
    -0.65
    ÃįÃį
    -0.64
     Rabbit
    -0.64
    POSITIVE LOGITS
    aration
    1.21
    arations
    1.13
    ension
    1.07
    uttering
    1.02
    ared
    1.02
    ine
    1.01
    arant
    1.00
    ensions
    0.99
    ined
    0.96
    aring
    0.96
    Act Density 0.012%

    No Known Activations