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

    Neuronpedia

    INDEX
    Explanations

    comparisons of quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases emphasizing quantity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilic
    -0.84
    DH
    -0.73
    ICAN
    -0.71
    adian
    -0.70
    ç·
    -0.70
    ranch
    -0.68
    ensis
    -0.68
    Express
    -0.67
    Interstitial
    -0.66
    ffen
    -0.65
    POSITIVE LOGITS
     doubling
    0.81
    whelming
    0.77
     half
    0.75
    atos
    0.74
    etheless
    0.73
     80
    0.72
     tripled
    0.70
     8000
    0.70
     doubled
    0.69
     anything
    0.68
    Act Density 0.039%

    No Known Activations