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

    Neuronpedia

    INDEX
    Explanations

    specific locations and measurements related to scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kie
    -0.92
    googleapis
    -0.78
     Khr
    -0.77
     Yahoo
    -0.76
     FRAG
    -0.75
    TestBed
    -0.75
     PDR
    -0.74
     Fior
    -0.72
     Ciri
    -0.72
    Oleg
    -0.71
    POSITIVE LOGITS
    Portale
    0.84
     Lincoln
    0.80
    COLN
    0.78
    raska
    0.76
     Talla
    0.74
    Lincoln
    0.72
     infierno
    0.70
    soul
    0.70
    ADAM
    0.68
     ADAM
    0.68
    Act Density 0.441%

    No Known Activations