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

    Neuronpedia

    INDEX
    Explanations

    references to injuries, death, and damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wright
    -0.15
     Fool
    -0.15
     Dion
    -0.15
    .scalablytyped
    -0.15
    ead
    -0.15
    ike
    -0.14
    .pa
    -0.14
    roke
    -0.14
    enne
    -0.14
    bard
    -0.14
    POSITIVE LOGITS
    æª
    0.17
    ahi
    0.15
    ENCHMARK
    0.14
    äºī
    0.14
    ãĥĥãĤ·ãĥ¥
    0.14
    àµ
    0.14
    ayar
    0.14
    ogr
    0.13
    lava
    0.13
    reasonable
    0.13
    Act Density 0.162%

    No Known Activations