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

    Neuronpedia

    INDEX
    Explanations

    phrases related to plotting or plans

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a significant or central plot in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     salts
    -0.63
    administ
    -0.63
     Voc
    -0.62
     Rio
    -0.62
    agles
    -0.62
     administering
    -0.62
     administ
    -0.62
    ogy
    -0.61
     experien
    -0.60
     certific
    -0.59
    POSITIVE LOGITS
    ters
    1.19
    lines
    1.14
    line
    1.10
    ter
    1.06
     twists
    1.03
     twist
    0.99
     hatched
    0.92
     Twist
    0.91
    ting
    0.90
    sov
    0.90
    Act Density 0.027%

    No Known Activations