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

    Neuronpedia

    INDEX
    Explanations

    words related to acknowledgment or agreement

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

    Ok and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TMS
    -0.47
    matrix
    -0.43
    mailer
    -0.43
    TMS
    -0.41
     frame
    -0.40
     Frame
    -0.39
    bison
    -0.38
    builder
    -0.38
     career
    -0.37
    campista
    -0.37
    POSITIVE LOGITS
     Ok
    2.08
    Ok
    1.95
     ok
    1.86
     OK
    1.68
     okay
    1.34
    OK
    1.30
    ok
    1.27
     Okay
    1.22
    isOk
    1.16
    Okay
    1.16
    Act Density 0.008%

    No Known Activations