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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orra
    -0.14
    پس
    -0.14
     flown
    -0.14
    orro
    -0.14
    inery
    -0.14
    ROP
    -0.13
    an
    -0.13
    iv
    -0.13
    edList
    -0.13
    殿
    -0.13
    POSITIVE LOGITS
    kus
    0.17
    ness
    0.16
     glad
    0.16
    acre
    0.15
    URLConnection
    0.15
    idity
    0.15
    lique
    0.14
    ÅĻich
    0.14
    ride
    0.14
    ucus
    0.14
    Act Density 0.023%

    No Known Activations