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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political or economic issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to risks and warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ription
    -0.64
     Norn
    -0.59
     sacrific
    -0.58
     orally
    -0.58
    DERR
    -0.58
     Annotations
    -0.57
     pictured
    -0.56
     includ
    -0.53
     greets
    -0.53
     Companion
    -0.53
    POSITIVE LOGITS
    NetMessage
    0.85
    Brexit
    0.71
    shr
    0.68
     weakness
    0.65
     attrition
    0.65
    political
    0.62
    appro
    0.62
     weakening
    0.61
    Weak
    0.60
     inev
    0.59
    Act Density 0.908%

    No Known Activations