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

    Neuronpedia

    INDEX
    Explanations

    mentions of freshness, particularly in relation to food

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fresh" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idget
    -0.71
    ureau
    -0.70
    adr
    -0.68
    king
    -0.67
    avior
    -0.64
    raints
    -0.64
    oris
    -0.62
     prohibits
    -0.61
    oret
    -0.60
    ometry
    -0.60
    POSITIVE LOGITS
     fresh
    1.05
    Fresh
    0.95
    ness
    0.89
    fresh
    0.84
     scratch
    0.81
    meat
    0.78
     fruits
    0.77
    lime
    0.77
    cit
    0.76
     rye
    0.75
    Act Density 0.010%

    No Known Activations