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

    Neuronpedia

    INDEX
    Explanations

    conversational statements and expressions of agreement or clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clas
    -0.16
    eden
    -0.16
    azu
    -0.15
    Abstract
    -0.15
    itud
    -0.15
    FP
    -0.14
    lettes
    -0.14
    ема
    -0.14
     Abstract
    -0.13
     entitlement
    -0.13
    POSITIVE LOGITS
    elper
    0.18
    iram
    0.15
     trÃŃ
    0.14
    ctest
    0.14
    coles
    0.14
    .scalablytyped
    0.14
    uide
    0.14
    rol
    0.14
    üny
    0.14
    .copyWith
    0.14
    Act Density 0.048%

    No Known Activations