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

    Neuronpedia

    INDEX
    Explanations

    references to novels and literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fully
    -0.17
    aan
    -0.17
    ÙĪØ·
    -0.15
     dán
    -0.15
    .Undef
    -0.15
    otence
    -0.15
    agit
    -0.14
    edar
    -0.14
    eload
    -0.14
    elerik
    -0.14
    POSITIVE LOGITS
    ists
    0.35
    ized
    0.31
    ization
    0.29
    izations
    0.29
    istic
    0.28
    -length
    0.28
    isation
    0.27
    ised
    0.27
    izing
    0.25
    ize
    0.25
    Act Density 0.024%

    No Known Activations