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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "like" appears

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uer
    -0.16
    ser
    -0.15
    getSingleton
    -0.15
    wert
    -0.15
    alian
    -0.14
     personalities
    -0.14
    FFFFFFFF
    -0.13
     text
    -0.13
     Fully
    -0.13
     fully
    -0.13
    POSITIVE LOGITS
    ebb
    0.18
    annel
    0.17
    -controls
    0.17
    rawer
    0.17
    istrovstvÃŃ
    0.16
     Sabb
    0.15
    ennie
    0.14
    µ
    0.14
    ream
    0.14
    ene
    0.14
    Act Density 0.009%

    No Known Activations