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

    Neuronpedia

    INDEX
    Explanations

    affirmations or expressions of agreement

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

    Saying "OK" at the beginning of a sentence

    np_acts-logits-general · gemini-2.0-flash

    agreement and proceeding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mappedBy
    -0.74
    AddTagHelper
    -0.68
    epam
    -0.65
    sidemargin
    -0.64
    UTERS
    -0.63
    twimg
    -0.62
     Wheeler
    -0.62
    //
    -0.58
    ResumeLayout
    -0.58
    postmedia
    -0.54
    POSITIVE LOGITS
    lahoma
    0.86
     OK
    0.82
     ok
    0.79
     Ok
    0.76
    Ok
    0.75
    alright
    0.74
     Alright
    0.73
     FINE
    0.71
    OK
    0.69
     Corral
    0.68
    Act Density 0.073%

    No Known Activations