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

    Neuronpedia

    INDEX
    Explanations

    references to virtual environments and reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elo
    -0.16
    наÑĢ
    -0.15
    alars
    -0.15
    ULO
    -0.15
    fal
    -0.15
    Vtbl
    -0.15
    alam
    -0.15
    adan
    -0.15
    ese
    -0.14
    aign
    -0.14
    POSITIVE LOGITS
    ization
    0.22
    ize
    0.22
    ized
    0.20
    isation
    0.19
    izing
    0.19
    ity
    0.18
    ities
    0.18
     flags
    0.16
    ising
    0.16
    ised
    0.16
    Act Density 0.015%

    No Known Activations