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

    Neuronpedia

    INDEX
    Explanations

    references to the act of slowly or gradually decreasing or diminishing

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     Stephen
    -0.78
    Stephen
    -0.73
    mappedBy
    -0.71
    Steam
    -0.70
     stephen
    -0.67
     Steam
    -0.66
     STEAM
    -0.64
     STEPHEN
    -0.63
    ⋙
    -0.62
    izowane
    -0.60
    POSITIVE LOGITS
     ste
    2.38
     nahilalakip
    0.65
     calendriers
    0.60
     nonatomic
    0.59
    FieldDescriptor
    0.58
    {{\
    0.56
    laye
    0.56
    ajinan
    0.56
     stew
    0.56
    ocarp
    0.55
    Act Density 0.000%

    No Known Activations