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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Fresh" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mund
    -0.70
    orset
    -0.69
    eering
    -0.66
     respecting
    -0.66
     mathemat
    -0.64
     surv
    -0.63
    ĸļ
    -0.63
    aldehyde
    -0.63
    ietal
    -0.62
    ccess
    -0.62
    POSITIVE LOGITS
    lings
    1.11
    water
    1.02
    ness
    1.00
    lish
    1.00
    ly
    0.99
    man
    0.92
    bread
    0.90
    lin
    0.88
    ling
    0.86
    faced
    0.86
    Act Density 0.004%

    No Known Activations