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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decreasing or diminishing quantities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reduction or scarcity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Discussion
    -0.72
    orthy
    -0.71
    dress
    -0.70
    icals
    -0.68
    ifi
    -0.67
    POL
    -0.67
     Correct
    -0.67
    iness
    -0.66
    ific
    -0.65
    ourced
    -0.65
    POSITIVE LOGITS
     violet
    0.77
     dwindling
    0.76
     extinct
    0.76
     caloric
    0.74
     losses
    0.73
     jaws
    0.73
     glaciers
    0.72
     ageing
    0.72
    Ń·
    0.71
     plummet
    0.71
    Act Density 0.021%

    No Known Activations