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

    Neuronpedia

    INDEX
    Explanations

    comparisons involving quantities or degrees

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases emphasizing a preference or desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilic
    -0.83
    DH
    -0.74
    ieri
    -0.74
    iless
    -0.72
    UCT
    -0.71
    adian
    -0.70
    rition
    -0.69
    ffen
    -0.69
    ucci
    -0.68
    oir
    -0.67
    POSITIVE LOGITS
     anything
    0.99
     doubling
    0.88
     ever
    0.83
     likely
    0.81
    etheless
    0.79
     usual
    0.79
    whelming
    0.78
     half
    0.76
     eighty
    0.75
     9000
    0.72
    Act Density 0.044%

    No Known Activations