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

    Neuronpedia

    INDEX
    Explanations

    actions related to removal or disassembly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iano
    -0.17
    stad
    -0.15
     Mush
    -0.15
    edith
    -0.15
    ervo
    -0.15
    akat
    -0.14
    atel
    -0.14
    agal
    -0.14
    aland
    -0.14
    åIJĪãĤıãģĽ
    -0.14
    POSITIVE LOGITS
    oter
    0.17
    ibel
    0.16
    AuthProvider
    0.15
    rnÄĽ
    0.14
    ken
    0.14
     Wol
    0.14
     Farrell
    0.14
    formatter
    0.14
    PACE
    0.14
     Lever
    0.13
    Act Density 0.075%

    No Known Activations