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

    Neuronpedia

    INDEX
    Explanations

    the word "stick" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "stick" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unfocusedRange
    -0.74
    OTO
    -0.74
    oding
    -0.69
    APH
    -0.68
    odes
    -0.67
    inators
    -0.66
    ĨĴ
    -0.65
    actionDate
    -0.65
     landscape
    -0.64
    ASED
    -0.64
    POSITIVE LOGITS
     stick
    1.18
     sticks
    1.03
     sticking
    0.87
    pipe
    0.86
     Stick
    0.85
     blender
    0.84
     burner
    0.84
    pole
    0.83
    lihood
    0.79
    handle
    0.79
    Act Density 0.007%

    No Known Activations