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

    Neuronpedia

    INDEX
    Explanations

    words related to superlatives

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "super."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reloaded
    -0.82
     Seym
    -0.79
     Lauder
    -0.69
    edIn
    -0.66
    aughs
    -0.65
    ynski
    -0.64
     Frie
    -0.64
    theless
    -0.64
     Anat
    -0.63
     Qiao
    -0.62
    POSITIVE LOGITS
    imposed
    1.24
    visor
    1.22
    cedes
    1.12
    nova
    1.11
    charged
    1.08
    visory
    1.04
    charg
    1.03
    visors
    1.01
    powers
    0.99
    computer
    0.99
    Act Density 0.016%

    No Known Activations