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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to appetite or strong desires

    oai_token-act-pair · gpt-3.5-turbo

    adjectives indicating an intense or extreme quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obyl
    -0.79
    erva
    -0.76
    eda
    -0.74
    ovember
    -0.73
    aret
    -0.70
     Surv
    -0.69
    nesota
    -0.69
    WAR
    -0.66
    ocard
    -0.64
    enhagen
    -0.64
    POSITIVE LOGITS
    nesses
    1.06
    ness
    0.91
    acious
    0.79
     eater
    0.78
     appet
    0.77
    minded
    0.73
    glers
    0.73
    Magikarp
    0.72
    ãĥ³ãĤ¸
    0.68
     curiosity
    0.66
    Act Density 0.027%

    No Known Activations