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

    Neuronpedia

    INDEX
    Explanations

    expressions related to personal interactions and actions

    oai_token-act-pair · gpt-3.5-turbo

    elements related to interactions and responses in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.69
    etheless
    -0.65
    iosyncr
    -0.58
     notably
    -0.58
    rupal
    -0.57
    20439
    -0.56
    eatures
    -0.55
     corrective
    -0.55
    ancies
    -0.55
     knowledgeable
    -0.54
    POSITIVE LOGITS
    !"
    1.54
    !".
    1.39
    !'
    1.36
    !",
    1.35
    !'"
    1.33
    !!"
    1.31
     âĢ¦"
    1.29
    ?!"
    1.28
    ?"
    1.26
    âĢ¦"
    1.22
    Act Density 0.644%

    No Known Activations