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

    Neuronpedia

    INDEX
    Explanations

    references to underground environments or hidden worlds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.18
    æĹĹ
    -0.17
    535
    -0.15
    å¡ļ
    -0.14
    .raises
    -0.14
    abal
    -0.14
    бÑĥдÑĮ
    -0.14
    รà¸ĵ
    -0.14
    aku
    -0.13
    619
    -0.13
    POSITIVE LOGITS
     hidden
    0.59
    hidden
    0.47
     secret
    0.47
     secrets
    0.44
     Hidden
    0.43
    -hidden
    0.41
    Hidden
    0.39
     concealed
    0.39
    éļIJèĹı
    0.37
     hiding
    0.36
    Act Density 0.083%

    No Known Activations