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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific concepts and elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Loop
    -0.16
    Loop
    -0.15
    onso
    -0.15
    ]={↵
    -0.15
    æ²¹
    -0.15
    ulle
    -0.15
    casts
    -0.14
     Pip
    -0.14
     katıl
    -0.14
     hum
    -0.14
    POSITIVE LOGITS
     fusion
    0.24
     nu
    0.23
     fiss
    0.22
     radioactive
    0.21
     bomb
    0.21
     Fusion
    0.21
     Decay
    0.21
     neutron
    0.20
     decay
    0.20
     drip
    0.20
    Act Density 0.002%

    No Known Activations