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

    Neuronpedia

    INDEX
    Explanations

    words related to coffee and related items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of coffee and jewelry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     provocation
    -0.79
     fracturing
    -0.71
     Wolves
    -0.67
     masturbation
    -0.65
     Maid
    -0.64
    jury
    -0.64
     Definition
    -0.63
     Capitals
    -0.62
     sled
    -0.62
     Madness
    -0.61
    POSITIVE LOGITS
    ese
    1.08
    ers
    1.05
    rael
    1.03
    ingly
    1.03
    arro
    1.00
    ees
    0.96
    ellery
    0.95
    eling
    0.94
    igel
    0.94
    icult
    0.94
    Act Density 0.014%

    No Known Activations