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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical specifications and instructions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their context in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pse
    -0.84
    umably
    -0.77
    lier
    -0.72
    bole
    -0.72
     metaphor
    -0.69
     stereotyp
    -0.68
     causation
    -0.67
     pessim
    -0.67
    ozyg
    -0.66
    ihara
    -0.65
    POSITIVE LOGITS
     Additionally
    1.49
     Includes
    1.36
     Lastly
    1.33
     Featuring
    1.28
     Whether
    1.27
     Along
    1.26
     Alternatively
    1.26
     Each
    1.25
     Furthermore
    1.23
     Also
    1.21
    Act Density 0.240%

    No Known Activations