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

    Neuronpedia

    INDEX
    Explanations

    instances of formatted text that might contain special characters or annotations like 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numerical dates or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uncond
    -0.70
     fug
    -0.69
     swat
    -0.69
     inactive
    -0.69
     prosec
    -0.68
     imperson
    -0.67
     answ
    -0.66
     stacks
    -0.65
     exha
    -0.65
     allied
    -0.65
    POSITIVE LOGITS
    Posted
    1.41
    ³³³³³³³³³³³³³³³³
    1.28
    ³³³³³³³³
    1.28
    posted
    1.27
    ³³³
    1.25
    Synopsis
    1.24
    ³³³³
    1.21
    ³³
    1.19
    Introduction
    1.18
    Born
    1.15
    Act Density 0.254%

    No Known Activations