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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to change or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥãĤ·ãĥ¥
    -0.15
    sted
    -0.15
    stad
    -0.14
    浦
    -0.14
     rov
    -0.13
    ToFit
    -0.13
    /browse
    -0.13
    eum
    -0.13
    ipa
    -0.13
    .JWT
    -0.12
    POSITIVE LOGITS
    nonnull
    0.15
    stdafx
    0.14
    umbo
    0.14
    ibold
    0.14
    som
    0.14
    AMY
    0.14
     Tamb
    0.14
     Mayer
    0.13
    neh
    0.13
    lod
    0.13
    Act Density 1.255%

    No Known Activations