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

    Neuronpedia

    INDEX
    Explanations

    references to parameters in mathematical equations or models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.87
    ■■
    -0.86
     pleaſure
    -0.86
     Camilo
    -0.81
     Tada
    -0.81
    Palla
    -0.81
     Palla
    -0.80
    !")
    -0.79
     Manufact
    -0.79
     Cæsar
    -0.78
    POSITIVE LOGITS
    theta
    1.93
     theta
    1.64
     θ
    1.50
    θ
    1.30
     Theta
    0.95
     يتيمه
    0.91
    Theta
    0.84
     ORIENT
    0.81
     orientations
    0.77
    Oriented
    0.77
    Act Density 0.059%

    No Known Activations