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

    Neuronpedia

    INDEX
    Explanations

    words related to discussion and consideration of various topics and issues

    oai_token-act-pair · gpt-3.5-turbo

    discussions about complex ideas and careful consideration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ®
    -0.69
    odox
    -0.64
    ML
    -0.63
    surprisingly
    -0.63
    translation
    -0.62
    20439
    -0.62
     è£ıè¦ļéĨĴ
    -0.62
     Previously
    -0.60
     penned
    -0.59
    itled
    -0.59
    POSITIVE LOGITS
    .'"
    1.11
    )."
    1.10
     âĢ¦"
    1.04
    .""
    1.01
    ."[
    1.01
    ."
    0.99
     ..."
    0.99
    .")
    0.91
    .''
    0.90
     fuckin
    0.89
    Act Density 1.159%

    No Known Activations