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

    Neuronpedia

    INDEX
    Explanations

    sequences of high-frequency words or phrases that contribute to various contexts and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NTN
    -0.20
    ollapsed
    -0.14
     spoiler
    -0.14
     Cancel
    -0.14
    ød
    -0.14
    lun
    -0.14
    ube
    -0.14
     infl
    -0.14
     ret
    -0.14
    jing
    -0.13
    POSITIVE LOGITS
    outu
    0.19
    usz
    0.16
    emet
    0.15
    igram
    0.15
    ẩu
    0.15
    ass
    0.15
    emey
    0.14
     McC
    0.14
     INCIDENT
    0.14
    IMA
    0.14
    Act Density 0.028%

    No Known Activations