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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'salt', with a particularly high activation for the exact word 'salt'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "salt."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.98
    vernment
    -0.82
    mercial
    -0.74
    GROUP
    -0.67
    ITNESS
    -0.66
    hler
    -0.66
     WARN
    -0.66
    STEP
    -0.65
    ufact
    -0.63
    GS
    -0.63
    POSITIVE LOGITS
    water
    1.13
    zman
    0.95
    bite
    0.93
    illo
    0.91
     baths
    0.89
    iness
    0.87
    osal
    0.85
    isbury
    0.83
    Salt
    0.83
     iod
    0.82
    Act Density 0.016%

    No Known Activations