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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "friends" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilt
    -0.16
    ILT
    -0.15
    ETY
    -0.14
    erse
    -0.14
    .codes
    -0.14
     decom
    -0.14
    oppins
    -0.14
    igger
    -0.14
    itian
    -0.14
    ebin
    -0.13
    POSITIVE LOGITS
    liness
    0.25
    lier
    0.24
    ship
    0.24
    ships
    0.23
    SHIP
    0.23
    liest
    0.20
    lies
    0.20
     WithEvents
    0.18
    Ship
    0.18
     Hosp
    0.15
    Act Density 0.018%

    No Known Activations