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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âng
    -0.16
    лаб
    -0.16
    aren
    -0.16
    upo
    -0.16
    arro
    -0.16
    ereco
    -0.15
    esc
    -0.15
    ãĤŃãĥ³ãĤ°
    -0.14
    oscope
    -0.14
    íݸ
    -0.14
    POSITIVE LOGITS
    224
    0.15
    297
    0.15
    iones
    0.15
     Whitney
    0.15
    sted
    0.15
    cak
    0.15
    utz
    0.14
    ãĤĴãģĭ
    0.14
    ernal
    0.14
     hypoth
    0.14
    Act Density 0.003%

    No Known Activations