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

    Neuronpedia

    INDEX
    Explanations

    words related to physical attributes, particularly those describing greenness or cleanliness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adelphia
    -0.19
     lParam
    -0.17
    ullah
    -0.16
    ìĬ¤íħĮ
    -0.16
    arine
    -0.16
    rophe
    -0.15
    ÌĨ
    -0.15
    ilities
    -0.15
    ulling
    -0.14
    .scalablytyped
    -0.14
    POSITIVE LOGITS
    Ùij
    0.16
    çĬ
    0.15
    er
    0.15
    न
    0.14
    erken
    0.14
    kt
    0.14
    esse
    0.14
    ks
    0.14
    inus
    0.14
    hn
    0.14
    Act Density 0.175%

    No Known Activations