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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific experiments and experiences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to experimental contexts or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Score
    -0.79
    tower
    -0.73
    sticks
    -0.69
     Cannes
    -0.66
    stick
    -0.66
    skirts
    -0.66
    aires
    -0.66
    naire
    -0.65
    alty
    -0.65
     Pact
    -0.64
    POSITIVE LOGITS
    ienced
    1.19
    iences
    0.98
    odox
    0.87
    ilit
    0.79
    iments
    0.77
    ience
    0.77
    ufact
    0.76
    ient
    0.75
    TS
    0.72
    ulously
    0.72
    Act Density 0.056%

    No Known Activations