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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms associated with preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.69
     <<<<<<<<<<<<<<
    -0.69
     Chwiliwch
    -0.63
     ब्रेकडाउन
    -0.62
     незавершена
    -0.61
    twimg
    -0.60
    scryfall
    -0.60
    Morfologia
    -0.59
    akhstan
    -0.56
    intios
    -0.55
    POSITIVE LOGITS
     preference
    1.02
    preference
    0.79
     replacement
    0.77
     Preference
    0.75
     preferred
    0.74
    Preference
    0.72
     preferences
    0.69
    preferred
    0.69
     replacing
    0.67
     replace
    0.66
    Act Density 0.221%

    No Known Activations