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

    Neuronpedia

    INDEX
    Explanations

    phrases related to speaking or addressing topics and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uma
    -0.15
    variants
    -0.14
    ãĤ
    -0.14
     exact
    -0.14
    ansson
    -0.14
    ÌĢ
    -0.14
    ÑĨионалÑĮ
    -0.14
    exact
    -0.14
    ormal
    -0.14
    orate
    -0.13
    POSITIVE LOGITS
    üstü
    0.15
    _patches
    0.15
    ãĥĥ
    0.14
    eldon
    0.14
    ypy
    0.14
    abilit
    0.14
    ymoon
    0.14
    d
    0.14
    edge
    0.14
    AccessType
    0.14
    Act Density 0.042%

    No Known Activations