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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and relational terms indicating ownership or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĥĨãĤ£
    -0.17
     fitte
    -0.17
    ahat
    -0.16
    ToProps
    -0.15
    inet
    -0.15
    INET
    -0.14
    άÏĥ
    -0.14
    zdy
    -0.14
    ahkan
    -0.14
    aidu
    -0.14
    POSITIVE LOGITS
     laps
    0.19
     lap
    0.18
     radar
    0.17
     Lap
    0.16
     possession
    0.16
    lap
    0.15
    abs
    0.15
    omba
    0.15
    adow
    0.15
    838
    0.14
    Act Density 0.175%

    No Known Activations