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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to size, extent, or importance

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate significance or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cling
    -0.86
    tag
    -0.78
    wich
    -0.77
    cker
    -0.75
    icle
    -0.74
    ney
    -0.73
    akers
    -0.73
    dar
    -0.72
    walk
    -0.71
    zen
    -0.70
    POSITIVE LOGITS
     amounts
    1.08
     quantities
    0.96
     amount
    0.88
     enormous
    0.83
     earthqu
    0.83
     cumbers
    0.81
     lengths
    0.81
     importance
    0.79
     proportions
    0.79
     leaps
    0.79
    Act Density 0.024%

    No Known Activations