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

    Neuronpedia

    INDEX
    Explanations

    the word "like" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jee
    -0.18
    habit
    -0.16
    bbing
    -0.16
    ufe
    -0.15
    REA
    -0.15
    chos
    -0.14
    ocache
    -0.14
    rieve
    -0.14
    iveau
    -0.14
    vů
    -0.14
    POSITIVE LOGITS
    ide
    0.17
    ider
    0.16
    ento
    0.15
     vengeance
    0.15
     Pent
    0.15
    ides
    0.14
    vier
    0.14
     Loy
    0.14
    apos
    0.14
     Morm
    0.14
    Act Density 0.013%

    No Known Activations