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

    Neuronpedia

    INDEX
    Explanations

    references to variable arguments in code or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.67
     negociar
    -0.61
     المعيارى
    -0.59
     regresó
    -0.59
     negociaciones
    -0.57
    úgó
    -0.56
     varones
    -0.56
    fjspx
    -0.55
     kemenangan
    -0.55
     liderança
    -0.55
    POSITIVE LOGITS
     Axis
    0.72
     arg
    0.71
     axis
    0.71
    arg
    0.70
    Axis
    0.63
     zoom
    0.62
     inv
    0.62
    Zoom
    0.61
    zoom
    0.59
     Zoom
    0.58
    Act Density 0.222%

    No Known Activations