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

    Neuronpedia

    INDEX
    Explanations

    references to virtual environments and related experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertime
    -0.16
    etrain
    -0.15
    aram
    -0.15
    NECT
    -0.15
    Vtbl
    -0.14
    ikan
    -0.14
    ese
    -0.14
    ervers
    -0.14
    hetto
    -0.14
    alars
    -0.14
    POSITIVE LOGITS
    ization
    0.20
    s
    0.19
    ized
    0.18
    isation
    0.18
    ize
    0.18
    /manual
    0.16
    izing
    0.16
     boundaries
    0.15
    izations
    0.15
     flags
    0.15
    Act Density 0.022%

    No Known Activations