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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    promotional phrases or instructions related to product addition and offers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hua
    -0.84
     ISIL
    -0.78
     Goldstein
    -0.77
     Cohn
    -0.72
     Jill
    -0.71
     ca
    -0.70
    ãĤ§
    -0.68
     Stella
    -0.68
    Wilson
    -0.68
     Elsa
    -0.67
    POSITIVE LOGITS
     4
    1.52
    4
    1.49
     Four
    1.15
    four
    1.14
     four
    1.11
    Four
    1.09
    Fourth
    0.96
     Fourth
    0.95
     fourth
    0.93
     IV
    0.92
    Act Density 0.234%

    No Known Activations