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

    Neuronpedia

    INDEX
    Explanations

    expressions related to structured or formal communication

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    o
    -0.57
    u
    -0.55
     back
    -0.54
    orn
    -0.54
    Wild
    -0.53
     Wild
    -0.52
    at
    -0.52
    Base
    -0.51
     Pe
    -0.50
     стру
    -0.49
    POSITIVE LOGITS
    WireFormatLite
    0.96
    ConstraintMaker
    0.96
     Мексичка
    0.86
     &___
    0.86
     Signalez
    0.83
    ViewFeatures
    0.77
    UIControlState
    0.73
    copg
    0.72
    SBATCH
    0.70
    yntaxException
    0.69
    Act Density 0.011%

    No Known Activations