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

    Neuronpedia

    INDEX
    Explanations

    questions and requests for feedback or input

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and questions related to user opinions or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     migr
    -0.68
     gamma
    -0.67
     nightly
    -0.67
    spir
    -0.66
     nons
    -0.61
     carriers
    -0.59
     glyph
    -0.58
    £ı
    -0.58
     footh
    -0.58
     stret
    -0.57
    POSITIVE LOGITS
    Answer
    1.37
     Answer
    1.07
     Nope
    1.04
    ?????-?????-
    0.98
    swers
    0.90
     answered
    0.80
    .?
    0.79
     answer
    0.79
    ?????-
    0.79
    answer
    0.77
    Act Density 0.275%

    No Known Activations