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

    Neuronpedia

    INDEX
    Explanations

    terms related to complex concepts and structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.91
    skosten
    -0.88
    ſelf
    -0.88
     wrappers
    -0.86
     originals
    -0.85
    smöglichkeiten
    -0.85
     poffible
    -0.85
     analogues
    -0.84
     successors
    -0.84
     messengers
    -0.84
    POSITIVE LOGITS
     situation
    0.52
     pair
    0.51
     version
    0.51
     bénéfices
    0.51
     piece
    0.51
     standpoint
    0.50
     program
    0.48
     system
    0.47
     strategy
    0.47
     émissions
    0.47
    Act Density 3.008%

    No Known Activations