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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.69
    SharedCtor
    -0.61
    ÁND
    -0.61
    ]--;
    -0.57
    antMatchers
    -0.55
    źni
    -0.54
    ++]=
    -0.54
    ISupport
    -0.53
    acamata
    -0.53
    җ
    -0.52
    POSITIVE LOGITS
     незавершена
    0.59
    :✨
    0.57
    клопе
    0.52
     consultato
    0.52
    HandlerContext
    0.51
     referrerpolicy
    0.50
    
    0.50
    Portail
    0.49
    Enllaces
    0.49
    ROIT
    0.48
    Act Density 0.005%

    No Known Activations