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

    Neuronpedia

    INDEX
    Explanations

    phrases signaling a transition or changing topic

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or transitional markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emo
    -0.68
    Ĺ
    -0.64
    İĭ
    -0.63
    oreal
    -0.62
    ļéĨĴ
    -0.60
    è¦ļéĨĴ
    -0.59
    ForgeModLoader
    -0.59
    lication
    -0.59
     playbook
    -0.58
    ģ
    -0.58
    POSITIVE LOGITS
     yeah
    0.91
     thank
    0.81
     uh
    0.78
     congratulations
    0.73
     yes
    0.71
     sir
    0.71
    yeah
    0.69
     Poor
    0.68
     Betsy
    0.68
     beware
    0.67
    Act Density 0.054%

    No Known Activations