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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numbers in a context not typically related to numerical values

    oai_token-act-pair · gpt-3.5-turbo

    quantifiers indicating frequency or quantity, such as "some" and "several."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.76
    cum
    -0.67
    livion
    -0.64
     âĢ¦"
    -0.64
    Ö
    -0.64
    omo
    -0.63
    ocracy
    -0.63
    ocratic
    -0.61
    arial
    -0.61
    âĹ¼
    -0.60
    POSITIVE LOGITS
    body
    0.89
    theless
    0.86
    een
    0.82
     Examples
    0.72
     irony
    0.71
    quartered
    0.71
     commenters
    0.70
    resa
    0.68
    eatures
    0.68
    tenance
    0.67
    Act Density 0.167%

    No Known Activations