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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases that involve the word "what."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stateProvider
    -0.55
     AssemblyCompany
    -0.55
    OrEqual
    -0.52
    UPDATED
    -0.51
    UnusedPrivate
    -0.49
    ください
    -0.49
    ثیر
    -0.48
     invokingState
    -0.48
    volte
    -0.48
    rootScope
    -0.47
    POSITIVE LOGITS
     happens
    0.98
     happened
    0.93
    ſo
    0.85
    soever
    0.81
    sApp
    0.74
     we
    0.73
     they
    0.71
    hever
    0.71
     happen
    0.69
    }{*}{}
    0.69
    Act Density 0.136%

    No Known Activations