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

    Neuronpedia

    INDEX
    Explanations

    connective and relational words that indicate dependencies or conditions between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unde
    -0.15
    anner
    -0.15
    Ordinal
    -0.14
     Bernstein
    -0.14
    INCREMENT
    -0.14
     Fortune
    -0.14
    amerate
    -0.13
    çĽ
    -0.13
     Bien
    -0.13
    415
    -0.13
    POSITIVE LOGITS
     Contrib
    0.17
    arResult
    0.15
    avra
    0.14
    krv
    0.14
    egers
    0.14
    ,strlen
    0.14
    ptune
    0.13
    avras
    0.13
    Svc
    0.13
     Sciences
    0.13
    Act Density 0.009%

    No Known Activations