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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal preferences and experiences related to positive and negative emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imus
    -0.15
    rances
    -0.14
    quisites
    -0.14
    ework
    -0.14
    htdocs
    -0.14
    rael
    -0.14
     Uncomment
    -0.14
    516
    -0.13
    ibel
    -0.13
     uncomment
    -0.13
    POSITIVE LOGITS
    ãĥ©ãĤ¤ãĥ³
    0.15
    LOCKS
    0.14
    åľ¨åľ°
    0.14
    ANS
    0.14
    èĭ
    0.13
    éłĨ
    0.13
    alarm
    0.13
     refrain
    0.13
     weather
    0.13
    ilog
    0.13
    Act Density 0.232%

    No Known Activations