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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflict or confrontation

    oai_token-act-pair · gpt-3.5-turbo

    commands and actions related to urgency or danger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.87
    xtap
    -0.81
     resil
    -0.72
    prisingly
    -0.71
    eatures
    -0.70
     obser
    -0.66
    ModLoader
    -0.66
    ibaba
    -0.65
    ailability
    -0.65
    aples
    -0.64
    POSITIVE LOGITS
    !"
    1.71
    !'"
    1.63
    !".
    1.63
    !",
    1.62
    !'
    1.52
    '"
    1.46
     ..."
    1.45
     âĢ¦"
    1.45
    ,'"
    1.45
    !!"
    1.44
    Act Density 0.378%

    No Known Activations