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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptors that signify status, quality, or prestige

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellan
    -0.14
    ÌĨ
    -0.14
     laure
    -0.14
    ãĥ©ãĥĥãĤ¯
    -0.13
     èĩ
    -0.13
    ÙĦÙĬÙģ
    -0.13
    ekim
    -0.13
    ENSIONS
    -0.13
    aven
    -0.13
    uang
    -0.13
    POSITIVE LOGITS
    lest
    0.15
    ly
    0.14
     "_
    0.14
    uye
    0.14
    letal
    0.14
    еÑĩно
    0.14
    celik
    0.14
     Gil
    0.14
    LY
    0.13
    946
    0.13
    Act Density 0.175%

    No Known Activations