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

    Neuronpedia

    INDEX
    Explanations

    terms related to declarations or statements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Decl" and its variations, indicating a focus on declarations or formal statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.89
     Hole
    -0.82
    âĶģ
    -0.76
    ÃįÃį
    -0.76
    culosis
    -0.75
     priv
    -0.72
    GROUND
    -0.71
    Interstitial
    -0.69
    nesday
    -0.69
    ~~~~
    -0.67
    POSITIVE LOGITS
    aration
    1.18
    ared
    1.14
    arations
    1.12
    uttering
    1.03
    aring
    1.01
    ine
    0.99
    ined
    0.96
    ension
    0.95
    utter
    0.94
    arant
    0.93
    Act Density 0.011%

    No Known Activations