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

    Neuronpedia

    INDEX
    Explanations

    expressions of belief or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arial
    -0.15
    Ïģκ
    -0.14
    ocrat
    -0.14
    enie
    -0.14
    ÏĨι
    -0.14
    ummings
    -0.14
    mia
    -0.14
    acea
    -0.14
    rips
    -0.13
    suit
    -0.13
    POSITIVE LOGITS
    ably
    0.22
    able
    0.19
     ye
    0.18
     me
    0.17
    abel
    0.16
    ability
    0.16
     yourselves
    0.15
     yourself
    0.15
    ibold
    0.15
    -you
    0.15
    Act Density 0.037%

    No Known Activations