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

    Neuronpedia

    INDEX
    Explanations

    words related to sticky objects or situations

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of "sticks."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UTH
    -0.86
    OTO
    -0.80
     unfocusedRange
    -0.75
    AMES
    -0.73
    APH
    -0.72
     Kirin
    -0.69
    EMBER
    -0.69
    HCR
    -0.69
     Rated
    -0.66
    oros
    -0.65
    POSITIVE LOGITS
    stick
    1.03
    erness
    0.98
     slic
    0.88
    sticks
    0.88
    wheel
    0.88
    lihood
    0.88
    pit
    0.87
    holders
    0.86
    pipe
    0.83
    pole
    0.83
    Act Density 0.007%

    No Known Activations