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

    Neuronpedia

    INDEX
    Explanations

    references to various units and their specifications or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edy
    -0.17
    irket
    -0.17
    suit
    -0.16
    leigh
    -0.16
    apiro
    -0.15
    orthand
    -0.15
    hound
    -0.15
    иÑĤов
    -0.14
    itag
    -0.14
    Ùĩ
    -0.14
    POSITIVE LOGITS
    errupted
    0.26
    uar
    0.17
    .scalablytyped
    0.17
    uitive
    0.16
    ually
    0.16
    /sub
    0.16
    ê°Ħ
    0.15
    lify
    0.15
    ual
    0.15
     NotSupportedException
    0.15
    Act Density 0.032%

    No Known Activations