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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing rankings or distinctions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uggle
    -0.62
    amel
    -0.59
    Fine
    -0.57
     Buff
    -0.57
    Ct
    -0.57
    CW
    -0.57
     Flavoring
    -0.57
    obyl
    -0.56
    inian
    -0.56
    abal
    -0.55
    POSITIVE LOGITS
     choice
    1.19
    choice
    1.01
     Week
    0.77
    eatures
    0.74
     Choice
    0.73
     eternity
    0.72
     Month
    0.70
    week
    0.66
    apixel
    0.66
     apocalypse
    0.65
    Act Density 0.791%

    No Known Activations