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

    Neuronpedia

    INDEX
    Explanations

    references to utopian themes or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SSION
    -0.17
    edi
    -0.16
    ofday
    -0.16
    haps
    -0.16
    haf
    -0.15
    hip
    -0.15
    hammer
    -0.15
    UMENT
    -0.15
    hawks
    -0.15
    ädchen
    -0.15
    POSITIVE LOGITS
    opian
    0.32
    opia
    0.29
    most
    0.28
    ters
    0.25
    recht
    0.23
    tar
    0.22
    imately
    0.22
    MOST
    0.22
    lim
    0.22
    tering
    0.22
    Act Density 0.013%

    No Known Activations