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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "rather" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ToBounds
    -0.87
    ActivityCompat
    -0.66
    xff
    -0.64
     Hass
    -0.63
    labelledby
    -0.63
    зу
    -0.63
     уч
    -0.62
    bells
    -0.62
    </b>
    -0.62
    ID
    -0.61
    POSITIVE LOGITS
    uttosto
    1.18
    rather
    1.11
     Rather
    1.05
    Rather
    1.04
     ***/
    0.97
     rather
    0.93
     guère
    0.91
     Fairly
    0.88
     Notion
    0.85
     Theſe
    0.82
    Act Density 0.065%

    No Known Activations