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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "obscure" and its variations, indicating a focus on hidden or lesser-known subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.16
    ookie
    -0.15
    onde
    -0.15
    tsky
    -0.15
    ippet
    -0.15
    ook
    -0.14
    pper
    -0.14
    ting
    -0.14
    ÑĤаж
    -0.14
    apt
    -0.14
    POSITIVE LOGITS
    uhe
    0.15
    ousel
    0.15
    ihn
    0.15
    inium
    0.14
    çŀ
    0.14
     heartbeat
    0.13
    âĢĮاÙĨ
    0.13
    ewis
    0.13
    avia
    0.13
    instr
    0.13
    Act Density 0.015%

    No Known Activations