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

    Neuronpedia

    INDEX
    Explanations

    first person pronouns, variants of "to be," or generally present tense

    oai_token-act-pair · gemini-2.0-flash

    phrases expressing self-reflection or personal state

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     parteci
    -0.71
    tagHelperRunner
    -0.66
    脚注の使い方
    -0.64
    Notae
    -0.60
     Италијани
    -0.59
    "]="
    -0.53
    licants
    -0.53
    حياتها
    -0.53
    photobucket
    -0.53
     autorité
    -0.52
    POSITIVE LOGITS
    apimachinery
    0.63
    ThroughAttribute
    0.53
    ]")]
    0.53
     wishing
    0.52
    typeorm
    0.52
    stateProvider
    0.50
     soir
    0.47
     AssemblyCulture
    0.47
     ter
    0.46
    IActionResult
    0.46
    Act Density 0.556%

    No Known Activations