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

    Neuronpedia

    INDEX
    Explanations

    short hyphenated phrases or words

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptors or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clause
    -0.70
     deduction
    -0.70
     Transparency
    -0.69
     amusement
    -0.67
     Improvement
    -0.67
     Savings
    -0.67
     logo
    -0.66
     reunion
    -0.65
     lineup
    -0.64
     Tsukuyomi
    -0.63
    POSITIVE LOGITS
    enough
    1.40
    eligible
    1.20
    compatible
    1.19
    served
    1.15
    tested
    1.13
    sufficient
    1.13
    aware
    1.11
    dependent
    1.10
    assed
    1.10
    existent
    1.09
    Act Density 0.155%

    No Known Activations