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

    Neuronpedia

    INDEX
    Explanations

    actions or verbs related to change and improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isma
    -0.17
    muz
    -0.16
    MAP
    -0.15
    ebe
    -0.14
    nett
    -0.14
     rum
    -0.14
    gis
    -0.14
    aña
    -0.14
    rowse
    -0.13
    ÑģÑĤва
    -0.13
    POSITIVE LOGITS
    elay
    0.15
    adies
    0.14
    abel
    0.14
    inth
    0.14
     intentional
    0.14
    ละ
    0.14
    odia
    0.14
    ĮĢ
    0.14
    eterminate
    0.13
     addCriterion
    0.13
    Act Density 0.041%

    No Known Activations