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

    Neuronpedia

    INDEX
    Explanations

    pieces of code and programming terms

    oai_token-act-pair · gpt-3.5-turbo

    elements of programming and technology language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Originally
    -0.49
    ranch
    -0.43
    olphins
    -0.41
    embed
    -0.40
    itled
    -0.40
    Thumbnail
    -0.39
    iq
    -0.39
    UGC
    -0.39
     âĢº
    -0.38
    toggle
    -0.38
    POSITIVE LOGITS
    )."
    0.63
    ]."
    0.63
    .''.
    0.56
    '."
    0.55
    .�
    0.54
    ''.
    0.52
    .'"
    0.52
    ."[
    0.52
    .''
    0.51
    .</
    0.50
    Act Density 3.936%

    No Known Activations