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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or participation rates among groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.75
    /**
    -0.71
    omiast
    -0.66
     Archiproducts
    -0.65
     Mountaine
    -0.64
    inthians
    -0.63
     ujednoznacz
    -0.63
    execSQL
    -0.62
     /**
    -0.61
    DockStyle
    -0.61
    POSITIVE LOGITS
     thôi
    0.71
     einzigen
    0.65
     seule
    0.64
    しか
    0.63
     einzige
    0.61
     slechts
    0.57
     barely
    0.57
     Übergang
    0.56
     only
    0.56
    ほん
    0.55
    Act Density 0.268%

    No Known Activations