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

    Neuronpedia

    INDEX
    Explanations

    words starting with "wo"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wo" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Magikarp
    -0.81
    ++++++++++++++++
    -0.75
    IUM
    -0.75
    oslov
    -0.67
    ividual
    -0.67
     Horowitz
    -0.67
    âĸ¬
    -0.65
    代
    -0.65
    idates
    -0.65
    itated
    -0.64
    POSITIVE LOGITS
    efully
    1.21
    ofer
    1.15
    ollen
    1.14
    eful
    1.14
    ocom
    1.01
    olly
    0.95
    onder
    0.91
    asted
    0.89
    aken
    0.88
    jo
    0.86
    Act Density 0.023%

    No Known Activations