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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating singular or unique items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    миÑĢ
    -0.15
    rej
    -0.14
    ISC
    -0.14
    .Expressions
    -0.14
    isci
    -0.14
    led
    -0.14
    keit
    -0.14
    ekil
    -0.13
    CustomAttributes
    -0.13
    jni
    -0.13
    POSITIVE LOGITS
    çon
    0.16
    à¹Ĥย
    0.16
    234
    0.15
    blick
    0.15
    rix
    0.15
    235
    0.15
     iota
    0.15
    üm
    0.14
     Late
    0.14
    olen
    0.14
    Act Density 0.054%

    No Known Activations