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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computing and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Houſe
    -0.76
     ſche
    -0.67
     purpoſe
    -0.67
     greateſt
    -0.66
     ſtre
    -0.65
     Monfieur
    -0.65
     Jefus
    -0.65
     Theſe
    -0.63
     ArrayAdapter
    -0.63
     againſt
    -0.63
    POSITIVE LOGITS
     tor
    0.63
    und
    0.61
     الاطلاع
    0.57
    fer
    0.55
     tre
    0.53
     Tor
    0.51
    tor
    0.50
     und
    0.48
    ulation
    0.48
     Toggle
    0.48
    Act Density 3.234%

    No Known Activations