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

    Neuronpedia

    INDEX
    Explanations

    affirmations or acknowledgments in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    okay and punctuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FetchType
    -0.43
     autorytatywna
    -0.42
     angeb
    -0.39
    twimg
    -0.37
    $_['
    -0.36
    ьаж
    -0.36
     thermodynamics
    -0.36
    XCTAssert
    -0.35
     preferential
    -0.35
     lux
    -0.34
    POSITIVE LOGITS
     Okay
    0.86
    Okay
    0.84
     okay
    0.77
    Alright
    0.74
     OKAY
    0.73
     OK
    0.73
    Ok
    0.73
    okay
    0.73
    Okey
    0.72
     ok
    0.71
    Act Density 0.070%

    No Known Activations