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

    Neuronpedia

    INDEX
    Explanations

    adjectives indicating strong or intense characteristics

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that convey extreme qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Weston
    -0.69
     Springer
    -0.65
     Bulg
    -0.62
     Entered
    -0.60
     Formation
    -0.59
     Reef
    -0.58
     Omega
    -0.58
     Takeru
    -0.58
     Schwe
    -0.57
     Naples
    -0.56
    POSITIVE LOGITS
    »
    1.25
    [/
    1.24
    "
    1.14
    '?
    1.11
    |
    1.07
    ''
    1.07
    ]'
    1.06
    *
    1.05
    theless
    1.05
    ãĢį
    1.04
    Act Density 0.432%

    No Known Activations