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

    Neuronpedia

    INDEX
    Explanations

    the word "obviously"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oil
    -0.16
    .LookAndFeel
    -0.16
    icks
    -0.15
    бо
    -0.15
    好äºĨ
    -0.14
    disk
    -0.14
    enk
    -0.14
    ÑĪев
    -0.14
     Tro
    -0.13
    Wizard
    -0.13
    POSITIVE LOGITS
    regor
    0.14
    eniz
    0.14
    anou
    0.14
    rome
    0.14
    reate
    0.13
    rosse
    0.13
     starred
    0.13
    indow
    0.13
    ifa
    0.13
    arat
    0.13
    Act Density 0.010%

    No Known Activations