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

    Neuronpedia

    INDEX
    Explanations

    terms related to control and regulation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Concat
    -0.57
    @
    -0.53
    спеди
    -0.50
    ub
    -0.49
    l
    -0.48
    onas
    -0.48
     kết
    -0.47
    rief
    -0.47
    kräf
    -0.47
    Ma
    -0.46
    POSITIVE LOGITS
    Controlling
    1.84
     controlling
    1.80
     Controlling
    1.79
     control
    1.74
     controlled
    1.74
    controlling
    1.74
     controls
    1.71
    Controlled
    1.70
    controlled
    1.70
     Controlled
    1.61
    Act Density 0.303%

    No Known Activations