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

    Neuronpedia

    INDEX
    Explanations

    words related to personal preferences and inclinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    individual preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inaug
    -0.60
     Wikimedijinoj
    -0.59
     feroit
    -0.55
    elevator
    -0.54
    原始内容存档
    -0.54
     plufieurs
    -0.53
    chränk
    -0.52
    tshell
    -0.52
     ISNI
    -0.52
    HasForeignKey
    -0.52
    POSITIVE LOGITS
     preference
    1.43
     preferences
    1.30
     Preference
    1.09
    preference
    0.99
     preferencia
    0.96
    preferences
    0.91
     Preferences
    0.88
     preferencias
    0.88
    Preference
    0.84
     preferred
    0.80
    Act Density 0.008%

    No Known Activations