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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating surprise or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ostavi
    -0.65
     nakalista
    -0.60
    tvguidetime
    -0.56
     <>",
    -0.56
     estimés
    -0.54
     oprot
    -0.53
     pending
    -0.50
    quis
    -0.48
     tentatively
    -0.48
      (
    -0.48
    POSITIVE LOGITS
    SuppressMessage
    0.63
    ArrowToggle
    0.60
    IBOutlet
    0.59
    不用
    0.55
    hoppers
    0.54
    schild
    0.53
     automatic
    0.52
    Jvm
    0.52
    SharedCtor
    0.51
    ệc
    0.51
    Act Density 0.233%

    No Known Activations