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

    Neuronpedia

    INDEX
    Explanations

    words related to cooking or grilling

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "grand" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phrine
    -0.80
    )=(
    -0.72
    vention
    -0.71
    hibition
    -0.68
    ership
    -0.67
    manship
    -0.66
    eers
    -0.63
    tics
    -0.63
    âĹ¼
    -0.63
     vitro
    -0.61
    POSITIVE LOGITS
    aciously
    1.19
    udging
    1.18
    udge
    1.18
    umpy
    1.14
    iffin
    1.14
    iddle
    1.04
    anny
    1.02
    illing
    1.02
    iddles
    1.01
    inder
    1.00
    Act Density 0.011%

    No Known Activations