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

    Neuronpedia

    INDEX
    Explanations

    expressions of confidence or assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¿
    -0.17
    ever
    -0.15
    arden
    -0.14
    ât
    -0.14
    ASET
    -0.14
    vier
    -0.14
    à¹Ģà¸Ħ
    -0.14
    \Active
    -0.14
    å½
    -0.13
    PLATFORM
    -0.13
    POSITIVE LOGITS
    ja
    0.19
     enough
    0.17
    ness
    0.15
    abi
    0.15
    877
    0.15
     Affairs
    0.15
    ancy
    0.14
     ja
    0.14
     Ja
    0.14
     affairs
    0.14
    Act Density 0.004%

    No Known Activations